Alok's banner
Alok's profile picture

Alok

@analogalok • 5,363 subscribers

Mechatronics Engineer AI belongs on your device. • Offline inference • No subscriptions. Teaching you to own your AI Intelligence Stack

Shorts

Qwen 3.8 27B (dense) running on a single RTX 4090 (24GB VRAM) at 65 tokens/sec decode with MTP! 260,000 context window or 65 tokens/sec decode with native MTP. The API cartel should be terrified. We are officially running frontier tier agentic AI (benchmarks comparable to claude opus 4.6 max) on a single consumer gaming GPU. I benchmarked Qwen3.8-27B on a single NVIDIA RTX 4090 (24GB VRAM, Ubuntu 22) using Unsloth’s Dynamic Q4_K_XL GGUF on the latest llama.cpp. Here is the complete benchmark breakdown across both Context Scaling and MTP Overdrive (28k prompt baseline): ### PART 1: The Context Scaling Matrix (Pure Throughput) # 1. Standard FP16 KV Cache (Unquantized): - 80k Context: 2,664.7 t/s prefill | 40.68 t/s decode | 22.36 GB VRAM - 100k Context: 2,678.7 t/s prefill | 40.89 t/s decode | 23.59 GB VRAM (100k is the hard ceiling for unquantized f16 KV in 24GB VRAM) # 2. Q8 Quantized KV Cache (-ctv q8_0 -ctk q8_0): - 130k Context: 2,639.1 t/s prefill | 40.96 t/s decode | 22.18 GB VRAM - 170k Context: 2,653.9 t/s prefill | 40.70 t/s decode | 23.68 GB VRAM (170k is the sweet spot for heavy agentic coding workflows) # 3. Q4 Quantized KV Cache (-ctv q4_0 -ctk q4_0): - 260k Context: 2,659.8 t/s prefill | 40.70 t/s decode | 23.00 GB VRAM Full 262k native context residing entirely in 24GB VRAM. Zero system RAM offload. Stress test with a monster 142k real-world prompt (-c 170000, Q8 KV): - Prefill: 1,829.50 tokens/s - Decode: 31.3 tokens/s - VRAM: 23.7 GB rock solid ### PART 2: Native MTP Overdrive (Trading Context for Speed) Since MTP heads are baked into the architecture, enabling native speculative drafting pushes decode speeds straight to 60 t/s with zero external draft model: # 1. MTP + Q8 KV Cache: - 80k Context: 2,370.66 t/s prefill | 59.25 t/s decode | 23.4 GB VRAM (MTP state buffers eat slightly more memory, making 80k the ceiling for Q8) # 2. MTP + Q4 KV Cache: - 130k Context: 2,391.09 t/s prefill | 60.10 t/s decode | 23.5 GB VRAM (Sweet spot: 130,000 context running at a screaming 60 tps decode) ### Qwen3.8-27B vs Muse Glimmer 30B Two days ago I benched Meta's Muse Glimmer 30B hitting 130k context unquantized (19.3 GB VRAM) pulling 50-75 t/s decode. If you own a single RTX 3090 or RTX 4090, you have zero excuse to burn API credits. ### The Reproduction llama.cpp flags: 1. Max Context Stack (260,000 Context @ 41 tps): ./build/bin/llama-server -m Qwen3.8-27B-UD-Q4_K_XL.gguf -c 260000 -ngl 99 --port 8080 -ctv q4_0 -ctk q4_0 2. MTP Overdrive Stack (130,000 Context @ 60 tps): ./build/bin/llama-server -m Qwen3.8-27B-UD-Q4_K_XL.gguf -c 130000 -ngl 99 --port 8080 -ctv q4_0 -ctk q4_0 --spec-type draft-mtp --spec-draft-n-max 4 --spec-draft-p-min 0.7 Unsloth's Hugging Face GGUF links, intelligence/agentic benchmark details, and performance charts are posted in the replies. Local compute is eating the cloud alive. How much monthly API spend does a 24GB setup like this actually replace for you?

Qwen 3.8 27B (dense) running on a single RTX 4090 (24GB VRAM) at 65 tokens/sec decode with MTP! 260,000 context window or 65 tokens/sec decode with native MTP. The API cartel should be terrified. We are officially running frontier tier agentic AI (benchmarks comparable to claude opus 4.6 max) on a single consumer gaming GPU. I benchmarked Qwen3.8-27B on a single NVIDIA RTX 4090 (24GB VRAM, Ubuntu 22) using Unsloth’s Dynamic Q4_K_XL GGUF on the latest llama.cpp. Here is the complete benchmark breakdown across both Context Scaling and MTP Overdrive (28k prompt baseline): ### PART 1: The Context Scaling Matrix (Pure Throughput) # 1. Standard FP16 KV Cache (Unquantized): - 80k Context: 2,664.7 t/s prefill | 40.68 t/s decode | 22.36 GB VRAM - 100k Context: 2,678.7 t/s prefill | 40.89 t/s decode | 23.59 GB VRAM (100k is the hard ceiling for unquantized f16 KV in 24GB VRAM) # 2. Q8 Quantized KV Cache (-ctv q8_0 -ctk q8_0): - 130k Context: 2,639.1 t/s prefill | 40.96 t/s decode | 22.18 GB VRAM - 170k Context: 2,653.9 t/s prefill | 40.70 t/s decode | 23.68 GB VRAM (170k is the sweet spot for heavy agentic coding workflows) # 3. Q4 Quantized KV Cache (-ctv q4_0 -ctk q4_0): - 260k Context: 2,659.8 t/s prefill | 40.70 t/s decode | 23.00 GB VRAM Full 262k native context residing entirely in 24GB VRAM. Zero system RAM offload. Stress test with a monster 142k real-world prompt (-c 170000, Q8 KV): - Prefill: 1,829.50 tokens/s - Decode: 31.3 tokens/s - VRAM: 23.7 GB rock solid ### PART 2: Native MTP Overdrive (Trading Context for Speed) Since MTP heads are baked into the architecture, enabling native speculative drafting pushes decode speeds straight to 60 t/s with zero external draft model: # 1. MTP + Q8 KV Cache: - 80k Context: 2,370.66 t/s prefill | 59.25 t/s decode | 23.4 GB VRAM (MTP state buffers eat slightly more memory, making 80k the ceiling for Q8) # 2. MTP + Q4 KV Cache: - 130k Context: 2,391.09 t/s prefill | 60.10 t/s decode | 23.5 GB VRAM (Sweet spot: 130,000 context running at a screaming 60 tps decode) ### Qwen3.8-27B vs Muse Glimmer 30B Two days ago I benched Meta's Muse Glimmer 30B hitting 130k context unquantized (19.3 GB VRAM) pulling 50-75 t/s decode. If you own a single RTX 3090 or RTX 4090, you have zero excuse to burn API credits. ### The Reproduction llama.cpp flags: 1. Max Context Stack (260,000 Context @ 41 tps): ./build/bin/llama-server -m Qwen3.8-27B-UD-Q4_K_XL.gguf -c 260000 -ngl 99 --port 8080 -ctv q4_0 -ctk q4_0 2. MTP Overdrive Stack (130,000 Context @ 60 tps): ./build/bin/llama-server -m Qwen3.8-27B-UD-Q4_K_XL.gguf -c 130000 -ngl 99 --port 8080 -ctv q4_0 -ctk q4_0 --spec-type draft-mtp --spec-draft-n-max 4 --spec-draft-p-min 0.7 Unsloth's Hugging Face GGUF links, intelligence/agentic benchmark details, and performance charts are posted in the replies. Local compute is eating the cloud alive. How much monthly API spend does a 24GB setup like this actually replace for you?

383,369 次观看

This is the most hilarious thing I saw and did today Ran gemma-4-12B-coder-fable5-composer2.5-v1-GGUF locally with 8 GB VRAM at 20+ tok/sec Anthropic's Claude Fable 5 launched June 9. By June 12 it was banned. I can't access it. You can't either. But here's the twist: I'm running a model trained on its chain of thought at 20 tok/s on my RTX 4060 8GB. Locally. Offline. No cloud. No export control. Enter: Gemma4-12B-Coder GGUF (Q4_K_M) Base: Google's gemma-4-12B-it Fine-tuned on verifiable Python CoT data: - Primary: Composer 2.5 real reasoning traces (only passing solutions kept) - Auxiliary: Fable 5 used to redo the hard cases Composer missed. Every training example's reasoning led to code that actually ran. No hallucinated logic. Llama.cpp flags: -m gemma4-coding-Q4_K_M.gguf -cnv -ngl 44 -c 64000 -v (huggingface model link in comments) Flag breakdown: -ngl 44 → offload 44 layers to GPU (tune this for your VRAM) -c 64000 → 64K context window -cnv → conversation/chat mode -v → verbose output The irony writes itself. Anthropic spent weeks telling the world Fable 5 (mythos) is too powerful to release. Then released it. Then got banned from serving it, including their own researchers. Meanwhile: a Gemma 4 12B fine tune, trained on Fable 5's reasoning, runs fully offline on my mid range consumer GPU No API. No cloud. Just me and llama.cpp. This is why local AI matters. Check out the model's link in the comments. How's your experience been with this model?

This is the most hilarious thing I saw and did today Ran gemma-4-12B-coder-fable5-composer2.5-v1-GGUF locally with 8 GB VRAM at 20+ tok/sec Anthropic's Claude Fable 5 launched June 9. By June 12 it was banned. I can't access it. You can't either. But here's the twist: I'm running a model trained on its chain of thought at 20 tok/s on my RTX 4060 8GB. Locally. Offline. No cloud. No export control. Enter: Gemma4-12B-Coder GGUF (Q4_K_M) Base: Google's gemma-4-12B-it Fine-tuned on verifiable Python CoT data: - Primary: Composer 2.5 real reasoning traces (only passing solutions kept) - Auxiliary: Fable 5 used to redo the hard cases Composer missed. Every training example's reasoning led to code that actually ran. No hallucinated logic. Llama.cpp flags: -m gemma4-coding-Q4_K_M.gguf -cnv -ngl 44 -c 64000 -v (huggingface model link in comments) Flag breakdown: -ngl 44 → offload 44 layers to GPU (tune this for your VRAM) -c 64000 → 64K context window -cnv → conversation/chat mode -v → verbose output The irony writes itself. Anthropic spent weeks telling the world Fable 5 (mythos) is too powerful to release. Then released it. Then got banned from serving it, including their own researchers. Meanwhile: a Gemma 4 12B fine tune, trained on Fable 5's reasoning, runs fully offline on my mid range consumer GPU No API. No cloud. Just me and llama.cpp. This is why local AI matters. Check out the model's link in the comments. How's your experience been with this model?

575,300 次观看

Qwen 3.8 27B Q4_K_M - 90 tokens/sec on a single NVIDIA RTX 4090 (24 GB VRAM) with Dflash2! (MTP 60 tps -> 90 tps Dflash2!!!!) Local AI moves so fast (literally!) it’s terrifying. Z lab just dropped DFlash 2 for Qwen 3.8 27b and Muse Glimmer. I patched llama.cpp (PR #27342) and paired it with Unsloth’s Qwen 3.8 27B UD-Q4_K_XL quant. The result? Lossless 90 tokens/s decode. My last post highlighted native MTP hitting 60 t/s at 130,000 context. But DFlash 2 just completely shattered that ceiling. By using parallel block diffusion drafting (predicting whole blocks of tokens in a single pass using dynamic convolutions), DFlash achieves a massive 5.39 token acceptance rate. THE ALPHA TWEAK: `n-max 7` eats too much VRAM for draft states. But if you drop the draft limit to `--spec-draft-n-max 4`, you slash the VRAM overhead and actually increase the throughput. Here is the new 24GB VRAM Physics Matrix (DFlash 2 @ n-max 4): - 30k Context: 1,725 t/s prefill | 87.05 t/s decode | 22.2 GB VRAM - 80k Context: 1,789 t/s prefill | 84.20 t/s decode | 23.3 GB VRAM - 110k Context: 1,767 t/s prefill | 83.35 t/s decode | 23.96 GB VRAM (110k context at 83+ tokens a second sitting exactly on the 24GB hardware limit is absolute wizardry). How to compile the PR today: git clone cd llama.cpp git fetch origin pull/27342/head:pr-27342 git switch pr-27342 cmake -B build -DGGML_CUDA=ON && cmake --build build -j Llama.cpp flags for Dflash (110k Context Ceiling): ./build/bin/llama-server -m Qwen3.8-27B-UD-Q4_K_XL.gguf -md Qwen3.8-27B-DFlash2-Q4_K_M.gguf --spec-type draft-dflash --spec-draft-n-max 4 -c 110000 -ngl 99 --port 8080 -ctv q4_0 -ctk q4_0 The fact that the open source community is shipping block diffusion drafters so quickly that run entirely locally on a gaming GPU is unbelievable. If you own a single RTX 3090 or 4090, it is officially time to upgrade to qwen 3.8 27b with dflash 2 and cancel your API subscriptions and let local silicon eat the cloud. This model beats GPT 5.6 Terra, GLM 5.2 DeepSeek V4 Pro, Muse Spark 1.2 and Claude Opus 4.8 on the artificial analysis agentic index (details in the replies) Hugging Face GGUF links (Base + DFlash2) and the full visual VRAM scaling and Dflash2 vs MTP graphs are also in the replies below. are you sticking to native MTP for the 130k context, or sacrificing 20k context to redline your decode speed? How many tokens/sec are you pushing on your current local rig?

Qwen 3.8 27B Q4_K_M - 90 tokens/sec on a single NVIDIA RTX 4090 (24 GB VRAM) with Dflash2! (MTP 60 tps -> 90 tps Dflash2!!!!) Local AI moves so fast (literally!) it’s terrifying. Z lab just dropped DFlash 2 for Qwen 3.8 27b and Muse Glimmer. I patched llama.cpp (PR #27342) and paired it with Unsloth’s Qwen 3.8 27B UD-Q4_K_XL quant. The result? Lossless 90 tokens/s decode. My last post highlighted native MTP hitting 60 t/s at 130,000 context. But DFlash 2 just completely shattered that ceiling. By using parallel block diffusion drafting (predicting whole blocks of tokens in a single pass using dynamic convolutions), DFlash achieves a massive 5.39 token acceptance rate. THE ALPHA TWEAK: `n-max 7` eats too much VRAM for draft states. But if you drop the draft limit to `--spec-draft-n-max 4`, you slash the VRAM overhead and actually increase the throughput. Here is the new 24GB VRAM Physics Matrix (DFlash 2 @ n-max 4): - 30k Context: 1,725 t/s prefill | 87.05 t/s decode | 22.2 GB VRAM - 80k Context: 1,789 t/s prefill | 84.20 t/s decode | 23.3 GB VRAM - 110k Context: 1,767 t/s prefill | 83.35 t/s decode | 23.96 GB VRAM (110k context at 83+ tokens a second sitting exactly on the 24GB hardware limit is absolute wizardry). How to compile the PR today: git clone cd llama.cpp git fetch origin pull/27342/head:pr-27342 git switch pr-27342 cmake -B build -DGGML_CUDA=ON && cmake --build build -j Llama.cpp flags for Dflash (110k Context Ceiling): ./build/bin/llama-server -m Qwen3.8-27B-UD-Q4_K_XL.gguf -md Qwen3.8-27B-DFlash2-Q4_K_M.gguf --spec-type draft-dflash --spec-draft-n-max 4 -c 110000 -ngl 99 --port 8080 -ctv q4_0 -ctk q4_0 The fact that the open source community is shipping block diffusion drafters so quickly that run entirely locally on a gaming GPU is unbelievable. If you own a single RTX 3090 or 4090, it is officially time to upgrade to qwen 3.8 27b with dflash 2 and cancel your API subscriptions and let local silicon eat the cloud. This model beats GPT 5.6 Terra, GLM 5.2 DeepSeek V4 Pro, Muse Spark 1.2 and Claude Opus 4.8 on the artificial analysis agentic index (details in the replies) Hugging Face GGUF links (Base + DFlash2) and the full visual VRAM scaling and Dflash2 vs MTP graphs are also in the replies below. are you sticking to native MTP for the 130k context, or sacrificing 20k context to redline your decode speed? How many tokens/sec are you pushing on your current local rig?

105,388 次观看

Run Gemma 4 26B MoE on 8GB VRAM with 250k context at 20+ tokens/sec If you own any 8GB VRAM graphics card, stop what you are doing. Local AI just had its absolute "Holy Shit" moment for budget hardware. Yesterday, I benchmarked Unsloth Gemma 4 12B Q4_K_XL on an 8GB card. The community went wild but immediately demanded more: "Can we run a 25B+ model on budget GPUs?" Today, I’m delivering exactly that. I am running a massive 26B parameter Mixture of Experts (MoE) model locally on a standard 8GB VRAM setup with 250k full native context!. If you own an RTX 3060, 3070, 4060, or any budget GPU with 8GB of VRAM, the local AI paradigm has completely changed. The performance metrics are astonishing: - 20 tokens/sec flat decode throughput. - Stable, flat decode speed even with massive prompts. - I threw a 60k token prompt at it, and it still clocked in at 20 TPS without dropping a single frame. # What about prefill? Yes, Time To First Token (TTFT) is slightly high when swallowing massive contexts. But with a solid 200 tokens/sec prefill speed, the wait is barely noticeable and highly usable. And this is running completely without Multi Token Prediction (MTP) active. How is this possible? It’s the magic of Google's new QAT (Quantization Aware Training) quants for Gemma 4. The model weight file (unsloth gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf) is only 13.2 GB, making it the ultimate local powerhouse. # The Test Setup: CPU: Intel Core i7 RAM: 16GB System RAM GPU: NVIDIA GeForce RTX 4060 Laptop GPU (8GB VRAM) # The Secret Sauce (The -cmoe Flag) To make this work properly on any 8GB card, you must use the -cmoe (CPU MoE) flag in llama.cpp. This flag isolates the heavy MoE expert weights directly to system memory (CPU/RAM) while letting your GPU focus strictly on the Attention layers and the KV Cache. It prevents VRAM spillage and holds the throughput rock solid. # The flags: -m "gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf" -cmoe -c 248000 -v Once running, just open the UI on localhost and toggle the new reasoning lightbulb icon in the text input box to watch the model perform multi step thinking. Are you still running smaller models, or are you ready to scale up your budget local setups? Let's discuss in the replies

Run Gemma 4 26B MoE on 8GB VRAM with 250k context at 20+ tokens/sec If you own any 8GB VRAM graphics card, stop what you are doing. Local AI just had its absolute "Holy Shit" moment for budget hardware. Yesterday, I benchmarked Unsloth Gemma 4 12B Q4_K_XL on an 8GB card. The community went wild but immediately demanded more: "Can we run a 25B+ model on budget GPUs?" Today, I’m delivering exactly that. I am running a massive 26B parameter Mixture of Experts (MoE) model locally on a standard 8GB VRAM setup with 250k full native context!. If you own an RTX 3060, 3070, 4060, or any budget GPU with 8GB of VRAM, the local AI paradigm has completely changed. The performance metrics are astonishing: - 20 tokens/sec flat decode throughput. - Stable, flat decode speed even with massive prompts. - I threw a 60k token prompt at it, and it still clocked in at 20 TPS without dropping a single frame. # What about prefill? Yes, Time To First Token (TTFT) is slightly high when swallowing massive contexts. But with a solid 200 tokens/sec prefill speed, the wait is barely noticeable and highly usable. And this is running completely without Multi Token Prediction (MTP) active. How is this possible? It’s the magic of Google's new QAT (Quantization Aware Training) quants for Gemma 4. The model weight file (unsloth gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf) is only 13.2 GB, making it the ultimate local powerhouse. # The Test Setup: CPU: Intel Core i7 RAM: 16GB System RAM GPU: NVIDIA GeForce RTX 4060 Laptop GPU (8GB VRAM) # The Secret Sauce (The -cmoe Flag) To make this work properly on any 8GB card, you must use the -cmoe (CPU MoE) flag in llama.cpp. This flag isolates the heavy MoE expert weights directly to system memory (CPU/RAM) while letting your GPU focus strictly on the Attention layers and the KV Cache. It prevents VRAM spillage and holds the throughput rock solid. # The flags: -m "gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf" -cmoe -c 248000 -v Once running, just open the UI on localhost and toggle the new reasoning lightbulb icon in the text input box to watch the model perform multi step thinking. Are you still running smaller models, or are you ready to scale up your budget local setups? Let's discuss in the replies

292,770 次观看

i just ran Google's brand new Unsloth Gemma4 12B dense GGUF on my RTX 4060 using llama.cpp + CUDA 13.2 21 tokens per second. on a budget consumer GPU. locally. no API. no cloud. no subscription. and the benchmarks are absolutely cooked # first let's talk architecture because this is genuinely different every multimodal model you've used has a frozen vision encoder + frozen audio encoder + LLM backbone glued together Gemma 4 12B is different it's a single decoder only transformer. that's it. vision? raw 48×48 pixel patches → one matmul → projected directly into the LLM audio? raw 16kHz signal sliced into 40ms frames → linear projection → same LLM input space no encoder tax. no latency penalty. no fragmented memory to put the encoder savings in perspective: old Gemma 4 26B approach: - 550M param vision encoder (frozen) - 300M param audio encoder (frozen) - LLM backbone Gemma 4 12B: - 35M param vision embedder (a single matmul) - no audio encoder at all - LLM backbone handles EVERYTHING 550M → 35M for vision alone. that's a 15x reduction this is why the gemma-4-12b-it-Q4_K_M.gguf is just 6.6 GBs!!! and it has 256K native context context # Benchmarks: AIME 2026 (math olympiad): 77.5% GPQA Diamond (expert science): 78.8% LiveCodeBench v6 (real code): 72% Codeforces ELO: 1659 MMLU Pro: 77.2% MATH-Vision: 79.7% BigBench Extra Hard: 53% inference → llama.cpp, LM Studio, vLLM, SGLang llamacpp flags: -m "gemma-4-12b-it-Q4_K_M.gguf" -ngl 99 -c 8000 -v --port 8080 Available on huggingface now! Link below

i just ran Google's brand new Unsloth Gemma4 12B dense GGUF on my RTX 4060 using llama.cpp + CUDA 13.2 21 tokens per second. on a budget consumer GPU. locally. no API. no cloud. no subscription. and the benchmarks are absolutely cooked # first let's talk architecture because this is genuinely different every multimodal model you've used has a frozen vision encoder + frozen audio encoder + LLM backbone glued together Gemma 4 12B is different it's a single decoder only transformer. that's it. vision? raw 48×48 pixel patches → one matmul → projected directly into the LLM audio? raw 16kHz signal sliced into 40ms frames → linear projection → same LLM input space no encoder tax. no latency penalty. no fragmented memory to put the encoder savings in perspective: old Gemma 4 26B approach: - 550M param vision encoder (frozen) - 300M param audio encoder (frozen) - LLM backbone Gemma 4 12B: - 35M param vision embedder (a single matmul) - no audio encoder at all - LLM backbone handles EVERYTHING 550M → 35M for vision alone. that's a 15x reduction this is why the gemma-4-12b-it-Q4_K_M.gguf is just 6.6 GBs!!! and it has 256K native context context # Benchmarks: AIME 2026 (math olympiad): 77.5% GPQA Diamond (expert science): 78.8% LiveCodeBench v6 (real code): 72% Codeforces ELO: 1659 MMLU Pro: 77.2% MATH-Vision: 79.7% BigBench Extra Hard: 53% inference → llama.cpp, LM Studio, vLLM, SGLang llamacpp flags: -m "gemma-4-12b-it-Q4_K_M.gguf" -ngl 99 -c 8000 -v --port 8080 Available on huggingface now! Link below

281,007 次观看

I told you to claim your free 16GB NVIDIA GPU for learning Local LLMs. Now I’m going to show you how to double its inference speed without touching the hardware. Google Colab gives you an enterprise grade NVIDIA Tesla T4 GPU for free, roughly 4 hours every single day. It is the absolute perfect sandbox for learning AI engineering, testing inference flags, and pushing massive context windows. The local AI timeline is moving way too fast. If you aren't using Multi Token Prediction (MTP) yet, you are leaving massive performance on the table. I just pushed DeepMind’s Gemma 4 26B to 64.9 t/s on this exact free tier. Let's look at the raw benchmark data running on an Ubuntu Linux environment with the latest compiled llama.cpp binaries and quantized GGUFs from Unsloth via HuggingFace: # Qwen 3.5 9B (Dense): Base: [ Prompt: 626.7 t/s | Generation: 21.0 t/s ] With MTP: [ Prompt: 539.1 t/s | Generation: 24.8 t/s ] # Gemma 4 26B QAT (MoE): Base: [ Prompt: 634.2 t/s | Generation: 48.3 t/s ] With MTP: [ Prompt: 572.1 t/s | Generation: 64.9 t/s ] If you are paying attention, this single Colab notebook reveals 3 massive observations about the current state of local LLMs: # 1. The MTP Speedup (Software Overclocking) Standard autoregressive decoding guesses one token at a time. MTP acts like a highly optimized, built in speculative decoder. It predicts multiple future tokens at once and the main model verifies them in parallel. The result? Zero accuracy loss and a massive throughput increase. Gemma jumped from 48 to 65 t/s just by flipping a flag. # 2. The MoE Paradox (Bigger is Faster) How does a 26B parameter model absolutely destroy a 9B model in raw speed on the exact same hardware? Architecture. Qwen 3.5 9B is a dense model. it activates all 9 billion parameters for every single token. Gemma 4 26B is a Mixture of Experts (MoE) model. It routes data efficiently, activating only 4B parameters per token. You get the reasoning capabilities of a 26B model with the compute cost of a 4B model. 3. Thinking Efficiency When I ran the exact same complex prompt on both models, the larger MoE spent significantly fewer "thinking" tokens to arrive at the correct answer. A smarter model doesn't just give better answers; it gets to the point faster, saving you compute cycles and preserving your context window. # Want to run this yourself? Here are the exact llama.cpp CLI commands. For Qwen (MTP is baked into the main model): ./llama-cli -m Qwen3.5-9B-UD-Q4_K_XL.gguf -p "Explain quantum computing." -n 2000 -c 8000 -ngl 99 -fa on --spec-type draft-mtp --spec-draft-n-max 4 --spec-draft-p-min 0.7 For Gemma (Using a separate lightweight draft model): ./llama-cli -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --model-draft mtp-gemma-4-26B-A4B-it.gguf -p "Explain quantum computing." -n 2000 -c 8000 -ngl 99 -fa on --spec-type draft-mtp --spec-draft-n-max 4 --spec-draft-p-min 0.7 Stop waiting for a $3,000 rig. Boot up Colab, pull these models, and start building your stack. I’ve put together a completely free, cell by cell Google Colab notebook that automates this entire workflow so you can test it yourself in 5 minutes and learn. Link to the notebook is in the comments below. Experiemt with different MTP parameters, context windows and post your results in the comments.

I told you to claim your free 16GB NVIDIA GPU for learning Local LLMs. Now I’m going to show you how to double its inference speed without touching the hardware. Google Colab gives you an enterprise grade NVIDIA Tesla T4 GPU for free, roughly 4 hours every single day. It is the absolute perfect sandbox for learning AI engineering, testing inference flags, and pushing massive context windows. The local AI timeline is moving way too fast. If you aren't using Multi Token Prediction (MTP) yet, you are leaving massive performance on the table. I just pushed DeepMind’s Gemma 4 26B to 64.9 t/s on this exact free tier. Let's look at the raw benchmark data running on an Ubuntu Linux environment with the latest compiled llama.cpp binaries and quantized GGUFs from Unsloth via HuggingFace: # Qwen 3.5 9B (Dense): Base: [ Prompt: 626.7 t/s | Generation: 21.0 t/s ] With MTP: [ Prompt: 539.1 t/s | Generation: 24.8 t/s ] # Gemma 4 26B QAT (MoE): Base: [ Prompt: 634.2 t/s | Generation: 48.3 t/s ] With MTP: [ Prompt: 572.1 t/s | Generation: 64.9 t/s ] If you are paying attention, this single Colab notebook reveals 3 massive observations about the current state of local LLMs: # 1. The MTP Speedup (Software Overclocking) Standard autoregressive decoding guesses one token at a time. MTP acts like a highly optimized, built in speculative decoder. It predicts multiple future tokens at once and the main model verifies them in parallel. The result? Zero accuracy loss and a massive throughput increase. Gemma jumped from 48 to 65 t/s just by flipping a flag. # 2. The MoE Paradox (Bigger is Faster) How does a 26B parameter model absolutely destroy a 9B model in raw speed on the exact same hardware? Architecture. Qwen 3.5 9B is a dense model. it activates all 9 billion parameters for every single token. Gemma 4 26B is a Mixture of Experts (MoE) model. It routes data efficiently, activating only 4B parameters per token. You get the reasoning capabilities of a 26B model with the compute cost of a 4B model. 3. Thinking Efficiency When I ran the exact same complex prompt on both models, the larger MoE spent significantly fewer "thinking" tokens to arrive at the correct answer. A smarter model doesn't just give better answers; it gets to the point faster, saving you compute cycles and preserving your context window. # Want to run this yourself? Here are the exact llama.cpp CLI commands. For Qwen (MTP is baked into the main model): ./llama-cli -m Qwen3.5-9B-UD-Q4_K_XL.gguf -p "Explain quantum computing." -n 2000 -c 8000 -ngl 99 -fa on --spec-type draft-mtp --spec-draft-n-max 4 --spec-draft-p-min 0.7 For Gemma (Using a separate lightweight draft model): ./llama-cli -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --model-draft mtp-gemma-4-26B-A4B-it.gguf -p "Explain quantum computing." -n 2000 -c 8000 -ngl 99 -fa on --spec-type draft-mtp --spec-draft-n-max 4 --spec-draft-p-min 0.7 Stop waiting for a $3,000 rig. Boot up Colab, pull these models, and start building your stack. I’ve put together a completely free, cell by cell Google Colab notebook that automates this entire workflow so you can test it yourself in 5 minutes and learn. Link to the notebook is in the comments below. Experiemt with different MTP parameters, context windows and post your results in the comments.

170,442 次观看

You don't need a GPU for fast studio grade voice cloning anymore. Qwen3 TTS (1.7B Q4_K_M) + mainline llama.cpp is officially the fastest way to generate zero shot voice clones using 100% pure CPU execution. Following up on my last post where we ran the Q8 model on a GPU, we just took local C++ voice synthesis a massive step further. The open source community quantized Alibaba's SOTA Qwen3 TTS model down to Q4_K_M GGUF, completely freeing local audio pipelines from dedicated graphics hardware. Here is the real world benchmark and hardware breakdown of running SOTA voice cloning on CPU: # Architecture & Model Setup Using Qwen3-TTS-12Hz-1.7B-Base-Q4_K_M.gguf paired with the 8 bit multimodal projector (mmproj-Q8_0.gguf), llama.cpp executes the entire pipeline in pure C++. No PyTorch, no CUDA dependencies, and no VRAM bottlenecks. # Real-World Memory Footprint - Baseline RAM: 1.6 GB system idle. - Peak Generation RAM: 8 GB RAM during active voice synthesis. - Requirement: Any basic machine with at least 8 GB of system RAM can run this easily. # Real World CPU Benchmarks - Google Colab Free Tier (Throttled 2 Core CPU): Synthesizes a 5 sec studio quality audio clip (~8 words) in 45 seconds. - Modern Consumer CPU (Intel i5/i7 13th/14th Gen or AMD Ryzen 7000/9000): generation should drop to 5 to 20 seconds (nearly 1:1 real-time generation speed!). # Zero Shot Voice Cloning Quality Pass any 5 to 20 second .wav audio sample to the C++ engine using the --tts-speaker-file flag. It yields clean, natural sounding cloned speech with virtually zero quality loss compared to unquantized FP16 weights. To make testing seamless, I built an updated zero config Google Colab notebook. It pulls the official pre built llama.cpp CPU binaries (zero compilation time!) launches a live Gradio web app right in your browser. Record a 5 second clip from your mic (or drop a .mp3, .wav file), type text, and generate cloned audio on CPU. Native C++ audio models are making edge based, offline AI voice agents a reality. Links to the free Q4 CPU Colab notebook and the Q4_K_M GGUF HuggingFace repository are in the replies below! Which models have you been running on your CPUs? What CPU hardware are you using for local inference?

You don't need a GPU for fast studio grade voice cloning anymore. Qwen3 TTS (1.7B Q4_K_M) + mainline llama.cpp is officially the fastest way to generate zero shot voice clones using 100% pure CPU execution. Following up on my last post where we ran the Q8 model on a GPU, we just took local C++ voice synthesis a massive step further. The open source community quantized Alibaba's SOTA Qwen3 TTS model down to Q4_K_M GGUF, completely freeing local audio pipelines from dedicated graphics hardware. Here is the real world benchmark and hardware breakdown of running SOTA voice cloning on CPU: # Architecture & Model Setup Using Qwen3-TTS-12Hz-1.7B-Base-Q4_K_M.gguf paired with the 8 bit multimodal projector (mmproj-Q8_0.gguf), llama.cpp executes the entire pipeline in pure C++. No PyTorch, no CUDA dependencies, and no VRAM bottlenecks. # Real-World Memory Footprint - Baseline RAM: 1.6 GB system idle. - Peak Generation RAM: 8 GB RAM during active voice synthesis. - Requirement: Any basic machine with at least 8 GB of system RAM can run this easily. # Real World CPU Benchmarks - Google Colab Free Tier (Throttled 2 Core CPU): Synthesizes a 5 sec studio quality audio clip (~8 words) in 45 seconds. - Modern Consumer CPU (Intel i5/i7 13th/14th Gen or AMD Ryzen 7000/9000): generation should drop to 5 to 20 seconds (nearly 1:1 real-time generation speed!). # Zero Shot Voice Cloning Quality Pass any 5 to 20 second .wav audio sample to the C++ engine using the --tts-speaker-file flag. It yields clean, natural sounding cloned speech with virtually zero quality loss compared to unquantized FP16 weights. To make testing seamless, I built an updated zero config Google Colab notebook. It pulls the official pre built llama.cpp CPU binaries (zero compilation time!) launches a live Gradio web app right in your browser. Record a 5 second clip from your mic (or drop a .mp3, .wav file), type text, and generate cloned audio on CPU. Native C++ audio models are making edge based, offline AI voice agents a reality. Links to the free Q4 CPU Colab notebook and the Q4_K_M GGUF HuggingFace repository are in the replies below! Which models have you been running on your CPUs? What CPU hardware are you using for local inference?

103,956 次观看

Free NVIDIA GPU with 16 GB VRAM GPU for Running Local LLMs! If you want to master local LLMs but you're waiting until you can afford a $1,500 GPU, you're honestly not going to make it. The open source AI ecosystem is moving way too fast for you to wait on your budget to catch up. Especially when you can build a bleeding edge inference engine from scratch right now, completely for free. You don't need a heavy local rig to start. Google is literally letting you use an enterprise grade NVIDIA Tesla T4 GPU for $0/hour. At standard cloud computing rates (~$0.20/hr), Google Colab’s 4 hour daily free tier hands you roughly $24 worth of data center tier GPU compute every single month. And most people just waste it. Let’s talk about the hardware you get access to for free. The NVIDIA Tesla T4 is an absolute workhorse: - Architecture: NVIDIA Turing (TU104) - VRAM: 16GB GDDR6 (320 GB/s bandwidth) - Compute: 320 Tensor Cores | 2560 CUDA Cores - Performance: 130 TOPS INT8 | 8.1 TFLOPS FP32 - Power: Sipping energy at a max 70W TDP This is the exact same hardware I used to run DeepMind's Gemma 4 26B A4B QAT MoE at a 250,000 context window without a single Out Of Memory (OOM) crash. If you have a web browser and 10 minutes, you have everything you need. I’ve put together a fully documented, cell by cell Google Colab notebook that teaches you exactly how to do this. Here is what the notebook actually teaches you: - How to provision an Ubuntu Linux environment with CUDA 13.0 and verify your driver stack. - How to pull the source code and compile the latest llama.cpp C++ binaries from scratch, specifically optimizing the build for your exact GPU using the -DCMAKE_CUDA_ARCHITECTURES=native flag. - How to directly download quantized local LLMs (GGUF format) straight from HuggingFace using the CLI. - How to manage 16GB VRAM limits, offload neural network layers to the GPU, and push massive context windows. Compile raw llama.cpp, ollama run a model, or spin up the LM Studio CLI. Pick whatever stack you are comfortable with. just start building. No hardware. No credit card. No excuses. Bookmark this post right now so you don't lose the tutorial. Even if you don't have time to run it today, you are going to want this workflow in your engineering toolkit. The link to the free Colab Notebook is in the comments below. Lemme know if you need more tutorials like this.

Free NVIDIA GPU with 16 GB VRAM GPU for Running Local LLMs! If you want to master local LLMs but you're waiting until you can afford a $1,500 GPU, you're honestly not going to make it. The open source AI ecosystem is moving way too fast for you to wait on your budget to catch up. Especially when you can build a bleeding edge inference engine from scratch right now, completely for free. You don't need a heavy local rig to start. Google is literally letting you use an enterprise grade NVIDIA Tesla T4 GPU for $0/hour. At standard cloud computing rates (~$0.20/hr), Google Colab’s 4 hour daily free tier hands you roughly $24 worth of data center tier GPU compute every single month. And most people just waste it. Let’s talk about the hardware you get access to for free. The NVIDIA Tesla T4 is an absolute workhorse: - Architecture: NVIDIA Turing (TU104) - VRAM: 16GB GDDR6 (320 GB/s bandwidth) - Compute: 320 Tensor Cores | 2560 CUDA Cores - Performance: 130 TOPS INT8 | 8.1 TFLOPS FP32 - Power: Sipping energy at a max 70W TDP This is the exact same hardware I used to run DeepMind's Gemma 4 26B A4B QAT MoE at a 250,000 context window without a single Out Of Memory (OOM) crash. If you have a web browser and 10 minutes, you have everything you need. I’ve put together a fully documented, cell by cell Google Colab notebook that teaches you exactly how to do this. Here is what the notebook actually teaches you: - How to provision an Ubuntu Linux environment with CUDA 13.0 and verify your driver stack. - How to pull the source code and compile the latest llama.cpp C++ binaries from scratch, specifically optimizing the build for your exact GPU using the -DCMAKE_CUDA_ARCHITECTURES=native flag. - How to directly download quantized local LLMs (GGUF format) straight from HuggingFace using the CLI. - How to manage 16GB VRAM limits, offload neural network layers to the GPU, and push massive context windows. Compile raw llama.cpp, ollama run a model, or spin up the LM Studio CLI. Pick whatever stack you are comfortable with. just start building. No hardware. No credit card. No excuses. Bookmark this post right now so you don't lose the tutorial. Even if you don't have time to run it today, you are going to want this workflow in your engineering toolkit. The link to the free Colab Notebook is in the comments below. Lemme know if you need more tutorials like this.

182,483 次观看

Run Gemma 4 26b MTP on 8 GB VRAM GPUs at 25+ tokens/second. Flags included! local llm space is moving at terminal velocity. only 3 days ago google released gemma 4 26b a4b qat quants. more efficient than before, ran on 8gb vram at 20 tok/sec. and now just a few hours ago, mainline llama.cpp merged a massive update and we just shattered our own record. decode throughput went 25-40% up on the same 8 GB VRAM setup! Before MTP: 20 tps -> After MTP: 28 tps! llama.cpp just officially merged PR #23398 ("add Gemma4 MTP"), bringing native Multi-Token Prediction (MTP) support to Gemma 4 models. By running speculative drafting on the same 8GB VRAM RTX 4060 setup, my decode throughput on a 64k context instantly leaped to a blistering 25–27 tokens/sec thats 25-30% increase with the same hardware. Here is the architectural catch you need to know: Unlike the Qwen 3.5 and 3.6 series, which bake the MTP heads directly into the base GGUF, the Gemma 4 MTP head is not built in. You must download a separate, specialized MTP drafter GGUF (the assistant model) to act as the speculator. (I've dropped the download link in the replies). copy and try the exact flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp --spec-draft-n-max 6 --spec-draft-p-min 0.7 --spec-draft-model gemma-4-26b-A4B-it-assistant-Q4_0.gguf -c 64000 -v n-max 4 and p-min 0.7 is also worth checking out. benchmark on your setup and workflow. if you have a single 8 gb vram nvidia rtx 4060, 3060, 3070, 2080, 2070, grab the MTP drafter GGUF link in the comments and try it yourself. Check it out even if you have asmaller or a larger gpu, such as a single rtx 3090, 4090, 3060, 2060. MTP works for all gemma 4 sizes such as gemma 4 12b, gemma 4 31b etc. but remember to grab the correct mtp draft assistant models respectively. what are you benchmarking today

Run Gemma 4 26b MTP on 8 GB VRAM GPUs at 25+ tokens/second. Flags included! local llm space is moving at terminal velocity. only 3 days ago google released gemma 4 26b a4b qat quants. more efficient than before, ran on 8gb vram at 20 tok/sec. and now just a few hours ago, mainline llama.cpp merged a massive update and we just shattered our own record. decode throughput went 25-40% up on the same 8 GB VRAM setup! Before MTP: 20 tps -> After MTP: 28 tps! llama.cpp just officially merged PR #23398 ("add Gemma4 MTP"), bringing native Multi-Token Prediction (MTP) support to Gemma 4 models. By running speculative drafting on the same 8GB VRAM RTX 4060 setup, my decode throughput on a 64k context instantly leaped to a blistering 25–27 tokens/sec thats 25-30% increase with the same hardware. Here is the architectural catch you need to know: Unlike the Qwen 3.5 and 3.6 series, which bake the MTP heads directly into the base GGUF, the Gemma 4 MTP head is not built in. You must download a separate, specialized MTP drafter GGUF (the assistant model) to act as the speculator. (I've dropped the download link in the replies). copy and try the exact flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp --spec-draft-n-max 6 --spec-draft-p-min 0.7 --spec-draft-model gemma-4-26b-A4B-it-assistant-Q4_0.gguf -c 64000 -v n-max 4 and p-min 0.7 is also worth checking out. benchmark on your setup and workflow. if you have a single 8 gb vram nvidia rtx 4060, 3060, 3070, 2080, 2070, grab the MTP drafter GGUF link in the comments and try it yourself. Check it out even if you have asmaller or a larger gpu, such as a single rtx 3090, 4090, 3060, 2060. MTP works for all gemma 4 sizes such as gemma 4 12b, gemma 4 31b etc. but remember to grab the correct mtp draft assistant models respectively. what are you benchmarking today

200,913 次观看

gemma-4-12B-agentic-fable5-composer2.5 V2 is out. the agentic upgrade to the model trained on Fable 5's reasoning. Running it now with TurboQuant llama.cpp on a single RTX 4060( 8 GB VRAM) at 30 tokens/second with full 25000 context and reasoning: # The benchmarks v2 is built for coding + agentic work. writing code, running commands, using tools, debugging, multi step technical tasks. The clearest signal is tau2 bench telecom, an agentic tool use benchmark whose diagnose → fix → verify loop mirrors real terminal/debugging work: tau2 bench telecom numbers: base Gemma 4 12B: ~15% this finetune: ~55%. (Self reported) thats a huge jump # TheTom/llama-cpp-turboquant flags: llama-server.exe -m gemma4-v2-Q4_K_M.gguf -ngl 99 -c 25000 --cache-type-k q8_0 --cache-type-v turbo3 --port 8080 Flag breakdown: -ngl 99 → full GPU offload -c 25000 → 25K context --cache-type-k q8_0 --cache-type-v turbo3 → mixed-precision KV cache — K at 8-bit, V at ~3-bit via TurboQuant (Walsh Hadamard rotated polar quant, Google's own KV-compression research). Not even merged into mainline llama.cpp. running it off a fork. No API. No cloud. Just llama.cpp. well, a fork of it and any 6gb+ GPU. If you tried yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF, check this out and share your experience with the models

gemma-4-12B-agentic-fable5-composer2.5 V2 is out. the agentic upgrade to the model trained on Fable 5's reasoning. Running it now with TurboQuant llama.cpp on a single RTX 4060( 8 GB VRAM) at 30 tokens/second with full 25000 context and reasoning: # The benchmarks v2 is built for coding + agentic work. writing code, running commands, using tools, debugging, multi step technical tasks. The clearest signal is tau2 bench telecom, an agentic tool use benchmark whose diagnose → fix → verify loop mirrors real terminal/debugging work: tau2 bench telecom numbers: base Gemma 4 12B: ~15% this finetune: ~55%. (Self reported) thats a huge jump # TheTom/llama-cpp-turboquant flags: llama-server.exe -m gemma4-v2-Q4_K_M.gguf -ngl 99 -c 25000 --cache-type-k q8_0 --cache-type-v turbo3 --port 8080 Flag breakdown: -ngl 99 → full GPU offload -c 25000 → 25K context --cache-type-k q8_0 --cache-type-v turbo3 → mixed-precision KV cache — K at 8-bit, V at ~3-bit via TurboQuant (Walsh Hadamard rotated polar quant, Google's own KV-compression research). Not even merged into mainline llama.cpp. running it off a fork. No API. No cloud. Just llama.cpp. well, a fork of it and any 6gb+ GPU. If you tried yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF, check this out and share your experience with the models

146,046 次观看

Muse Glimmer, A 30B parameter dense model swallowing a 130,000 token context window using only 19.3 GB of VRAM (extreme efficiency). No KV cache quantization required. I just benched the new Muse Glimmer 30B (dense) on a single RTX 4090. We are pulling 3,100+ t/s prefill and 75 tokens/second decode. The throughput is violent. Meta superintelligence lab just open sourced this agentic beast, explicitly engineered to dominate 24GB consumer cards. I pulled the latest llama.cpp source on Ubuntu 22 (CUDA 13) to see if the specs were real. Fed it a 28k token prompt. Here is the exact llama.cpp God Stack and benchmarking breakdown: # 1. The Deep Context Run (No Speculative Decoding) The architecture uses a massive 16:1 GQA (Grouped Query Attention) ratio. This means the KV cache footprint is practically non existent. ./build/bin/llama-server -m Muse-Glimmer-30B-UD-Q4_K_XL.gguf -c 130000 -b 4096 -ub 4096 -ngl 99 --port 8080 Prefill: 3134.95 t/s Decode: 50.00 t/s VRAM: 19.34 GB (I hit 130k context on pristine, unquantized f16 cache and still had 4.5 GB of VRAM left over. Absolute witchcraft). # 2. The DFlash Speculative Overdrive Meta shipped this with a DFlash block diffusion drafter. Let's trade that extra VRAM for pure speed. ./build/bin/llama-server -m Muse-Glimmer-30B-UD-Q4_K_XL.gguf -md dflash-kquant.gguf --spec-type draft-dflash --spec-draft-n-max 3 -c 80000 -b 4096 -ub 4096 -ngl 99 --port 8080 Prefill: 1293.69 t/s Decode: 75.00 t/s VRAM: 23.93 GB (Maxed out on card) the dflash gguf is additional 1.6 GBs # The Architecture Insight (Muse Glimmer vs. Gemma 4 31B) If you look at my Gemma 4 31B tests from last week, getting 140k context required heavily degrading the memory with Q4 KV quantization (gemma 31b q4 can do only about 40k context with unquantized kv on a 24gb card). That "unzipping" overhead bottlenecked Gemma's MTP decode speeds down to 65 t/s. Muse Glimmer completely sidesteps this bottleneck. By using aggressive 16:1 GQA, it keeps the KV cache in native f16 format at massive context lengths. Flash Attention gets to run at maximum uncompressed speed, letting the DFlash drafter push decode safely to 75 t/s without compute lag. With a 76% on SWE Bench Verified and seamless local tool calling, this model looks promising. Unsloth's Hugging Face GGUF links, intelligence/agentic benchmark details, and inference throughput performance graphs are posted in the replies. For 24GB rig, what’s your current go to model?

Muse Glimmer, A 30B parameter dense model swallowing a 130,000 token context window using only 19.3 GB of VRAM (extreme efficiency). No KV cache quantization required. I just benched the new Muse Glimmer 30B (dense) on a single RTX 4090. We are pulling 3,100+ t/s prefill and 75 tokens/second decode. The throughput is violent. Meta superintelligence lab just open sourced this agentic beast, explicitly engineered to dominate 24GB consumer cards. I pulled the latest llama.cpp source on Ubuntu 22 (CUDA 13) to see if the specs were real. Fed it a 28k token prompt. Here is the exact llama.cpp God Stack and benchmarking breakdown: # 1. The Deep Context Run (No Speculative Decoding) The architecture uses a massive 16:1 GQA (Grouped Query Attention) ratio. This means the KV cache footprint is practically non existent. ./build/bin/llama-server -m Muse-Glimmer-30B-UD-Q4_K_XL.gguf -c 130000 -b 4096 -ub 4096 -ngl 99 --port 8080 Prefill: 3134.95 t/s Decode: 50.00 t/s VRAM: 19.34 GB (I hit 130k context on pristine, unquantized f16 cache and still had 4.5 GB of VRAM left over. Absolute witchcraft). # 2. The DFlash Speculative Overdrive Meta shipped this with a DFlash block diffusion drafter. Let's trade that extra VRAM for pure speed. ./build/bin/llama-server -m Muse-Glimmer-30B-UD-Q4_K_XL.gguf -md dflash-kquant.gguf --spec-type draft-dflash --spec-draft-n-max 3 -c 80000 -b 4096 -ub 4096 -ngl 99 --port 8080 Prefill: 1293.69 t/s Decode: 75.00 t/s VRAM: 23.93 GB (Maxed out on card) the dflash gguf is additional 1.6 GBs # The Architecture Insight (Muse Glimmer vs. Gemma 4 31B) If you look at my Gemma 4 31B tests from last week, getting 140k context required heavily degrading the memory with Q4 KV quantization (gemma 31b q4 can do only about 40k context with unquantized kv on a 24gb card). That "unzipping" overhead bottlenecked Gemma's MTP decode speeds down to 65 t/s. Muse Glimmer completely sidesteps this bottleneck. By using aggressive 16:1 GQA, it keeps the KV cache in native f16 format at massive context lengths. Flash Attention gets to run at maximum uncompressed speed, letting the DFlash drafter push decode safely to 75 t/s without compute lag. With a 76% on SWE Bench Verified and seamless local tool calling, this model looks promising. Unsloth's Hugging Face GGUF links, intelligence/agentic benchmark details, and inference throughput performance graphs are posted in the replies. For 24GB rig, what’s your current go to model?

65,480 次观看

Qwen 3.8 Flash Next (125B A6B MoE) Vs Qwen 3.8 27B (dense) - Both Q4_K_XL - Reasoning Off Prompt: Create a very high quality realistic video like animation of the solar system. three.js via cdn. Let the camera revolve around. single html file. dont call any tools. dont need any controls. Qwen 3.8 27b focused on computational physics & geometry (inclinations, coordinate math, moon orbits). While Qwen 3.8 125B A6B focused on cinematography & visual UX (lighting contrast, atmospheric glow, framing, and HUD overlays). It also followed the camera instruction correctly and produced result thats visually more stunning. Both the models run on single RTX 3090/4090 (24 GB VRAM). the 27b will fit entirely in the VRAM, but you'd need 100-120GB RAM for the new 125B MoE (check out the previous post for complete inference benchmarks and llama.cpp setup) Qwen 3.8 Flash Next beats Qwen 3.8 27B in almost all the benchmarks. have dropped the intelligence benchmark comparison and unsloth quant huggingface links in the replies. Which one would u be running regularly on your hardware?

Qwen 3.8 Flash Next (125B A6B MoE) Vs Qwen 3.8 27B (dense) - Both Q4_K_XL - Reasoning Off Prompt: Create a very high quality realistic video like animation of the solar system. three.js via cdn. Let the camera revolve around. single html file. dont call any tools. dont need any controls. Qwen 3.8 27b focused on computational physics & geometry (inclinations, coordinate math, moon orbits). While Qwen 3.8 125B A6B focused on cinematography & visual UX (lighting contrast, atmospheric glow, framing, and HUD overlays). It also followed the camera instruction correctly and produced result thats visually more stunning. Both the models run on single RTX 3090/4090 (24 GB VRAM). the 27b will fit entirely in the VRAM, but you'd need 100-120GB RAM for the new 125B MoE (check out the previous post for complete inference benchmarks and llama.cpp setup) Qwen 3.8 Flash Next beats Qwen 3.8 27B in almost all the benchmarks. have dropped the intelligence benchmark comparison and unsloth quant huggingface links in the replies. Which one would u be running regularly on your hardware?

33,836 次观看

50% more context unlocked for Qwen 3.8 27b Q4_K_XL dflash 2 on a single RTX 4090 (24 GB VRAM) I found a hidden VRAM tax in llama.cpp. By combining my custom 2 bit DFlash 2 drafter with one overlooked server flag, I just unlocked another +80,000 tokens of context. Qwen3.8-27B is now running a massive 250,000 context at 75 tokens/s on a single RTX 4090. Here is the secret: By default, `llama-server` reserves massive chunks of your VRAM to handle multiple concurrent users (batching). If you are running a single user session, you are bleeding memory for features you aren't using. By passing the `--parallel 1` flag, you force the engine to dedicate 100% of your 24GB VRAM buffer to a single user. When we combine the VRAM saved by our Q2_K 2-bit drafter with the VRAM saved by `--parallel 1`, the context ceilings absolutely explode: Note: all benchmarks carried out with a massive 28k prompt. Ubuntu 22. ### THE NEW 24GB PHYSICAL LIMITS (Single RTX 4090): # 1. The "Repo Swallower" (Q4 KV Cache): - Context: 250,000 tokens (Up from 170k!) - Speed: 73.66 t/s decode | 1,608 t/s prefill - Peak VRAM: 23.8 GB # 2. The "High-Precision SWE" (Q8 KV Cache): - Context: 150,000 tokens (Up from 100k!) - Speed: 75.01 t/s decode | 1,667 t/s prefill - Peak VRAM: 23.9 GB # 3. The "Pristine Attention" (Unquantized FP16 KV): - Context: 90,000 tokens - Speed: 80.58 t/s decode | 1,699 t/s prefill - Peak VRAM: 23.92 GB ### HOW TO RUN THE 250K GOD STACK TODAY: (Requires PR #27342 + my Q2_K Hugging Face drafter) llama.cpp flags: ./build/bin/llama-server -m Qwen3.8-27B-UD-Q4_K_XL.gguf -md Qwen3.8-27B-DFlash2-Q2_K.gguf --spec-type draft-dflash --spec-draft-n-max 3 -c 250000 -ngl 99 --parallel 1 --port 8080 -ctv q4_0 -ctk q4_0 We are pushing a quarter million tokens of context with speculative DFlash 2 decoding at 73 tokens/second on a single consumer gaming GPU. I dropped my custom 2 bit Hugging Face GGUF links, visual performance graphs, and the PR #27342 build instructions in the replies below. If you own a single RTX 3090 or 4090, it is officially time to cancel your API subscriptions and let local silicon eat the cloud. how much monthly API spend does an optimized 4090 rig like this actually replace for you?

50% more context unlocked for Qwen 3.8 27b Q4_K_XL dflash 2 on a single RTX 4090 (24 GB VRAM) I found a hidden VRAM tax in llama.cpp. By combining my custom 2 bit DFlash 2 drafter with one overlooked server flag, I just unlocked another +80,000 tokens of context. Qwen3.8-27B is now running a massive 250,000 context at 75 tokens/s on a single RTX 4090. Here is the secret: By default, `llama-server` reserves massive chunks of your VRAM to handle multiple concurrent users (batching). If you are running a single user session, you are bleeding memory for features you aren't using. By passing the `--parallel 1` flag, you force the engine to dedicate 100% of your 24GB VRAM buffer to a single user. When we combine the VRAM saved by our Q2_K 2-bit drafter with the VRAM saved by `--parallel 1`, the context ceilings absolutely explode: Note: all benchmarks carried out with a massive 28k prompt. Ubuntu 22. ### THE NEW 24GB PHYSICAL LIMITS (Single RTX 4090): # 1. The "Repo Swallower" (Q4 KV Cache): - Context: 250,000 tokens (Up from 170k!) - Speed: 73.66 t/s decode | 1,608 t/s prefill - Peak VRAM: 23.8 GB # 2. The "High-Precision SWE" (Q8 KV Cache): - Context: 150,000 tokens (Up from 100k!) - Speed: 75.01 t/s decode | 1,667 t/s prefill - Peak VRAM: 23.9 GB # 3. The "Pristine Attention" (Unquantized FP16 KV): - Context: 90,000 tokens - Speed: 80.58 t/s decode | 1,699 t/s prefill - Peak VRAM: 23.92 GB ### HOW TO RUN THE 250K GOD STACK TODAY: (Requires PR #27342 + my Q2_K Hugging Face drafter) llama.cpp flags: ./build/bin/llama-server -m Qwen3.8-27B-UD-Q4_K_XL.gguf -md Qwen3.8-27B-DFlash2-Q2_K.gguf --spec-type draft-dflash --spec-draft-n-max 3 -c 250000 -ngl 99 --parallel 1 --port 8080 -ctv q4_0 -ctk q4_0 We are pushing a quarter million tokens of context with speculative DFlash 2 decoding at 73 tokens/second on a single consumer gaming GPU. I dropped my custom 2 bit Hugging Face GGUF links, visual performance graphs, and the PR #27342 build instructions in the replies below. If you own a single RTX 3090 or 4090, it is officially time to cancel your API subscriptions and let local silicon eat the cloud. how much monthly API spend does an optimized 4090 rig like this actually replace for you?

39,189 次观看

I just got Gemma 4 26B A4B MoE model running fully locally with Hermes agent on an 8GB RTX 4060 and it's now backtesting trading strategies end to end, no hand holding. If you’re a trader or work on Wall Street, you don’t want to miss this. Yes. fully automated. No cloud. No APIs beyond market data. # Here's what I did: Setup: - Model: Gemma 4 26B-A4B QAT (MoE), Q4_K_XL Unsloth's quant (link in the comments) - Inference: llama.cpp (turboquant fork by Tom Turney link in the comments) - Hardware: RTX 4060, 8GB VRAM + 16GB RAM only (with 50 other chrome tabs open) - Context: 64K llama.cpp turboquant flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 64000 --cache-type-k q8_0 --cache-type-v turbo3 --port 8080 turboquant helps achieve high prefill and decode throughput for interactive sessions. throughput with Hermes agent: decode: 25+ tokens/sec prefill: 250+ tokens/sec # Then I gave the agent one task: Backtest a strategy: - Buy when RSI crosses above 30 - Sell at +2% profit or -1% stoploss - No overlapping positions - Use Google stock via yfinance - Generate a full HTML report with candlestick charts + signals What happened next was wild. It didn't just write code, it ran the entire workflow itself: Audited the environment (pip list, dependency check) Hit a ModuleNotFoundError, multiple Python installs were conflicting Ran where python to map every interpreter on the system Manually selected the correct Python 3.13 path and re ran the script Wrote a clean statevmachine backtester (strict no overlapping trades logic) Patched a yfinance MultiIndex quirk that would've crashed the script Built Plotly candlestick + RSI charts with buy/sell markers Calculated win rate, PnL, and summary stats Exported a polished single file HTML report. check the report at the end of the video or in the comments. Biggest takeaway: local LLMs aren't just "chat assistants" anymore. They debug their own environment, write production code, and ship a finished deliverable on consumer hardware, for $0 in API costs. If you're still calling local models "toys," you're already behind. This is just the beginning. Hermes agent just surpassed 1 trillion tokens in a single day on OpenRouter. Think about the scale of total token generation happening right now. Disclaimer: This is not financial advice. Consult a professional before making any trading decisions.

I just got Gemma 4 26B A4B MoE model running fully locally with Hermes agent on an 8GB RTX 4060 and it's now backtesting trading strategies end to end, no hand holding. If you’re a trader or work on Wall Street, you don’t want to miss this. Yes. fully automated. No cloud. No APIs beyond market data. # Here's what I did: Setup: - Model: Gemma 4 26B-A4B QAT (MoE), Q4_K_XL Unsloth's quant (link in the comments) - Inference: llama.cpp (turboquant fork by Tom Turney link in the comments) - Hardware: RTX 4060, 8GB VRAM + 16GB RAM only (with 50 other chrome tabs open) - Context: 64K llama.cpp turboquant flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 64000 --cache-type-k q8_0 --cache-type-v turbo3 --port 8080 turboquant helps achieve high prefill and decode throughput for interactive sessions. throughput with Hermes agent: decode: 25+ tokens/sec prefill: 250+ tokens/sec # Then I gave the agent one task: Backtest a strategy: - Buy when RSI crosses above 30 - Sell at +2% profit or -1% stoploss - No overlapping positions - Use Google stock via yfinance - Generate a full HTML report with candlestick charts + signals What happened next was wild. It didn't just write code, it ran the entire workflow itself: Audited the environment (pip list, dependency check) Hit a ModuleNotFoundError, multiple Python installs were conflicting Ran where python to map every interpreter on the system Manually selected the correct Python 3.13 path and re ran the script Wrote a clean statevmachine backtester (strict no overlapping trades logic) Patched a yfinance MultiIndex quirk that would've crashed the script Built Plotly candlestick + RSI charts with buy/sell markers Calculated win rate, PnL, and summary stats Exported a polished single file HTML report. check the report at the end of the video or in the comments. Biggest takeaway: local LLMs aren't just "chat assistants" anymore. They debug their own environment, write production code, and ship a finished deliverable on consumer hardware, for $0 in API costs. If you're still calling local models "toys," you're already behind. This is just the beginning. Hermes agent just surpassed 1 trillion tokens in a single day on OpenRouter. Think about the scale of total token generation happening right now. Disclaimer: This is not financial advice. Consult a professional before making any trading decisions.

105,094 次观看

llama.cpp isn't just for text LLMs anymore. Pure C++ zero shot voice cloning just officially landed in mainline. Text generation was only step one. If you’re building autonomous local AI agents, real time voice assistants, or edge workflows, instant low latency audio is the missing piece. Thanks to PR #26254, Alibaba’s state of the art Qwen3 TTS model family is now natively supported directly inside the llama.cpp repository under the multimodal (mtmd) framework. No Python bloat. No massive PyTorch CUDA overhead. Just raw, hyper optimized C++ running GGUF voice weights. Here is why this native update is a massive deal for the open source local AI stack: # Multimodal Architecture (.gguf + mmproj) Qwen3-TTS splits the workload between the base language model backbone and a multimodal projection adapter. llama.cpp handles this using the llama-tts binary, mapping the text model alongside its --mmproj projector to process audio tokens seamlessly. # Zero Shot Voice Cloning in Seconds You don't need fine tuning or massive dataset training. Feed the C++ engine a single 5 to 10 second .wav audio sample using the --tts-speaker-file flag, and it accurately clones the exact timbre, tone, and accent on the fly. # Real World T4 GPU Benchmark & Resource FootprintRunning the 1.7B Base model in 8-bit quantization (Q8_0): - VRAM Footprint: ~7 GB peak VRAM during active zero-shot cloning. - Audio Quality: Studio grade, natural-sounding voice output in seconds. • - Execution: Direct execution via native compiled binaries or sub process calls. # Coming Next to llama-server (PR #26603) Beyond CLI execution, a native POST /tts HTTP endpoint is currently being added to llama-server, which will soon allow you to trigger voice generation directly via standard REST API requests! # quick note on Colab compilation: Because this code was merged into mainline very recently, pre-built third-party binaries haven't fully caught up yet. Compiling llama-tts directly from source on Google Colab's free CPU instance can take about 1 hour (or ~1-2 minutes if targeting single GPU arch like -DCMAKE_CUDA_ARCHITECTURES=75). Be patient during the build step, or compile it locally on your own rig for instant execution! To test this out yourself, I built a zero config Google Colab notebook that compiles llama.cpp, downloads the Q8_0 GGUF files from HuggingFace, and spins up an interactive Gradio Studio UI so you can record/upload 3 second clips and clone voices in real time. Stop sleeping on native C++ audio. The era of bulky Python audio pipelines is officially over. Links to the free Google Colab notebook and the official ggml org GGUF HuggingFace model repository are in the replies below! available in q4 and q8 both variants, 1 GB and 1.85 GBs respectively (requires additional ~500MB mmproj gguf) Are you building local voice agents yet? What does your current audio stack look like? Drop your setups below!

llama.cpp isn't just for text LLMs anymore. Pure C++ zero shot voice cloning just officially landed in mainline. Text generation was only step one. If you’re building autonomous local AI agents, real time voice assistants, or edge workflows, instant low latency audio is the missing piece. Thanks to PR #26254, Alibaba’s state of the art Qwen3 TTS model family is now natively supported directly inside the llama.cpp repository under the multimodal (mtmd) framework. No Python bloat. No massive PyTorch CUDA overhead. Just raw, hyper optimized C++ running GGUF voice weights. Here is why this native update is a massive deal for the open source local AI stack: # Multimodal Architecture (.gguf + mmproj) Qwen3-TTS splits the workload between the base language model backbone and a multimodal projection adapter. llama.cpp handles this using the llama-tts binary, mapping the text model alongside its --mmproj projector to process audio tokens seamlessly. # Zero Shot Voice Cloning in Seconds You don't need fine tuning or massive dataset training. Feed the C++ engine a single 5 to 10 second .wav audio sample using the --tts-speaker-file flag, and it accurately clones the exact timbre, tone, and accent on the fly. # Real World T4 GPU Benchmark & Resource FootprintRunning the 1.7B Base model in 8-bit quantization (Q8_0): - VRAM Footprint: ~7 GB peak VRAM during active zero-shot cloning. - Audio Quality: Studio grade, natural-sounding voice output in seconds. • - Execution: Direct execution via native compiled binaries or sub process calls. # Coming Next to llama-server (PR #26603) Beyond CLI execution, a native POST /tts HTTP endpoint is currently being added to llama-server, which will soon allow you to trigger voice generation directly via standard REST API requests! # quick note on Colab compilation: Because this code was merged into mainline very recently, pre-built third-party binaries haven't fully caught up yet. Compiling llama-tts directly from source on Google Colab's free CPU instance can take about 1 hour (or ~1-2 minutes if targeting single GPU arch like -DCMAKE_CUDA_ARCHITECTURES=75). Be patient during the build step, or compile it locally on your own rig for instant execution! To test this out yourself, I built a zero config Google Colab notebook that compiles llama.cpp, downloads the Q8_0 GGUF files from HuggingFace, and spins up an interactive Gradio Studio UI so you can record/upload 3 second clips and clone voices in real time. Stop sleeping on native C++ audio. The era of bulky Python audio pipelines is officially over. Links to the free Google Colab notebook and the official ggml org GGUF HuggingFace model repository are in the replies below! available in q4 and q8 both variants, 1 GB and 1.85 GBs respectively (requires additional ~500MB mmproj gguf) Are you building local voice agents yet? What does your current audio stack look like? Drop your setups below!

47,881 次观看

90% of "AI developers" just download pre packaged GGUF files from Hugging Face, hit run, and call it a day. The top 10% know how to pull the raw safetensors, run the math, and quantize massive models into Q4_K_M themselves. If you think llama.cpp can only execute models, you’re missing the best part of the open source ecosystem. It’s a high performance optimization suite. Manually stripping 69% of the VRAM footprint off a brand new model architecture is where real infrastructure value is made. If you want to actually master local inference and deploy models like Google’s massive Gemma 4 12B it on consumer NVIDIA hardware using llama.cpp, you need to learn this pipeline. Let's build it. I just took the raw 22.7 GB Gemma 4 baseline and manually compressed it down to a 7.02 GB Q4_K_M GGUF artifact using llama.cpp. That is a 69% reduction in footprint. No quality loss. No VRAM bottlenecks. Just native, hardware accelerated C++ inference running a full 2,50,000 token context window on a dual NVIDIA Tesla T4 setup. Stop melting your VRAM on unoptimized weights and stop relying on other people's pipelines. Own your stack. I mapped this entire architecture from dynamic binary fetching to raw quantization and real time GPU streaming into a single, bulletproof notebook. Notebook link is in the comments below. Bookmark this blueprint for your next deployment and tell me which quantization works best for your workflow and model.

90% of "AI developers" just download pre packaged GGUF files from Hugging Face, hit run, and call it a day. The top 10% know how to pull the raw safetensors, run the math, and quantize massive models into Q4_K_M themselves. If you think llama.cpp can only execute models, you’re missing the best part of the open source ecosystem. It’s a high performance optimization suite. Manually stripping 69% of the VRAM footprint off a brand new model architecture is where real infrastructure value is made. If you want to actually master local inference and deploy models like Google’s massive Gemma 4 12B it on consumer NVIDIA hardware using llama.cpp, you need to learn this pipeline. Let's build it. I just took the raw 22.7 GB Gemma 4 baseline and manually compressed it down to a 7.02 GB Q4_K_M GGUF artifact using llama.cpp. That is a 69% reduction in footprint. No quality loss. No VRAM bottlenecks. Just native, hardware accelerated C++ inference running a full 2,50,000 token context window on a dual NVIDIA Tesla T4 setup. Stop melting your VRAM on unoptimized weights and stop relying on other people's pipelines. Own your stack. I mapped this entire architecture from dynamic binary fetching to raw quantization and real time GPU streaming into a single, bulletproof notebook. Notebook link is in the comments below. Bookmark this blueprint for your next deployment and tell me which quantization works best for your workflow and model.

62,631 次观看

Right now, you may not have access to models like GPT‑5.6 Sol, GPT‑4.6 Terra, GPT‑5.6 Luna, Claude Mythos 5, or Claude Fable 5. But you can run something surprisingly powerful today, locally, and completely free. in the next 10 mins on your 8 GB VRAM gaming laptop. Gemma 4 26B A4B QAT (MoE) delivers strong performance on a standard 8 GB VRAM GPU using Ollama, with no API, no usage limits, and no external dependencies. Out of the box, it reaches around 20 tokens per second without any optimizations. Only one command in your terminal: Ollama run gemma4:26b This means: Full offline capability (privacy by default) Zero recurring cost Competitive performance for many real world tasks Fast enough for interactive use on cheap consumer hardware If you're waiting for cutting edge cloud models, you're missing what is already practical today: a capable, local LLM that runs entirely on your own machine.

Right now, you may not have access to models like GPT‑5.6 Sol, GPT‑4.6 Terra, GPT‑5.6 Luna, Claude Mythos 5, or Claude Fable 5. But you can run something surprisingly powerful today, locally, and completely free. in the next 10 mins on your 8 GB VRAM gaming laptop. Gemma 4 26B A4B QAT (MoE) delivers strong performance on a standard 8 GB VRAM GPU using Ollama, with no API, no usage limits, and no external dependencies. Out of the box, it reaches around 20 tokens per second without any optimizations. Only one command in your terminal: Ollama run gemma4:26b This means: Full offline capability (privacy by default) Zero recurring cost Competitive performance for many real world tasks Fast enough for interactive use on cheap consumer hardware If you're waiting for cutting edge cloud models, you're missing what is already practical today: a capable, local LLM that runs entirely on your own machine.

65,387 次观看

If you thought the Gemma 4 31B (dense) model was fast, sit down. I just benched the updated Gemma 4 26B A4B MoE on a single RTX 4090 (24 GB VRAM) 9,200 t/s prefill. 160 t/s decode. 250,000 context window. All on a single consumer RTX 4090. The numbers are completely unhinged. The 31B is a dense behemoth. But the 26B is a Mixture of Experts (MoE), specifically an Active 4 Billion (A4B). It holds 26B parameters of knowledge but only activates 4B per token. Because its inference memory footprint is so light, I didn’t even need KV cache quantization to hit a quarter million context. Compiled the latest llama.cpp from source on Ubuntu 22 (CUDA 13). Fed it a 28k token prompt, and manually cranked the batch sizes (-b 2048 -ub 2048) to absolutely redline the Tensor Cores. Here is the benchmarking breakdown: # 1. The Baseline (No MTP) Even without speculative decoding, the A4B architecture flies. llama.cpp flags: ./build/bin/llama-server -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 250000 -ngl 99 -fa on -b 2048 -ub 2048 --port 8080 -v Context Ceiling: 250,000 tokens (21.5 GB VRAM) Prefill: 9,200 t/s (Absurd) Decode: 124 t/s # 2. The MTP Overdrive Injected the new MTP draft model to enable Speculative Decoding. llama.cpp flags: ./build/bin/llama-server -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp --spec-draft-model mtp-gemma-4-26B-A4B-it.gguf --spec-draft-n-max 4 --spec-draft-p-min 0.7 -c 250000 -ngl 99 -fa on -b 2048 -ub 2048 --port 8080 -v Context Ceiling: 250,000 tokens (22.96 GB VRAM) Prefill: 7,054 t/s (MTP draft overhead slightly caps prefill) Decode: 156 t/s # The Agentic Architecture Insight Why does this matter? Because you can now build a killer local agentic loop on a consumer desktop. Use the 31B dense model (from the previous post) as your heavy, deliberate Orchestrator / Verifier / Planner. Pass the actual execution tasks to this 26B MoE. At 160 t/s, this MoE can chew through code generation, tool calling, and massive RAG document retrieval over a 250k context window almost instantly, drastically speeding up your agentic loop. If you own a single RTX 3090 or 4090 and haven't tried this specific stack yet, you need to pull these latest updates and run it. Local inference just leveled up. Hugging Face links to the Unsloth 26B QAT quants and MTP drafters are in the replies. performance graphs also available in the replies.

If you thought the Gemma 4 31B (dense) model was fast, sit down. I just benched the updated Gemma 4 26B A4B MoE on a single RTX 4090 (24 GB VRAM) 9,200 t/s prefill. 160 t/s decode. 250,000 context window. All on a single consumer RTX 4090. The numbers are completely unhinged. The 31B is a dense behemoth. But the 26B is a Mixture of Experts (MoE), specifically an Active 4 Billion (A4B). It holds 26B parameters of knowledge but only activates 4B per token. Because its inference memory footprint is so light, I didn’t even need KV cache quantization to hit a quarter million context. Compiled the latest llama.cpp from source on Ubuntu 22 (CUDA 13). Fed it a 28k token prompt, and manually cranked the batch sizes (-b 2048 -ub 2048) to absolutely redline the Tensor Cores. Here is the benchmarking breakdown: # 1. The Baseline (No MTP) Even without speculative decoding, the A4B architecture flies. llama.cpp flags: ./build/bin/llama-server -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 250000 -ngl 99 -fa on -b 2048 -ub 2048 --port 8080 -v Context Ceiling: 250,000 tokens (21.5 GB VRAM) Prefill: 9,200 t/s (Absurd) Decode: 124 t/s # 2. The MTP Overdrive Injected the new MTP draft model to enable Speculative Decoding. llama.cpp flags: ./build/bin/llama-server -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp --spec-draft-model mtp-gemma-4-26B-A4B-it.gguf --spec-draft-n-max 4 --spec-draft-p-min 0.7 -c 250000 -ngl 99 -fa on -b 2048 -ub 2048 --port 8080 -v Context Ceiling: 250,000 tokens (22.96 GB VRAM) Prefill: 7,054 t/s (MTP draft overhead slightly caps prefill) Decode: 156 t/s # The Agentic Architecture Insight Why does this matter? Because you can now build a killer local agentic loop on a consumer desktop. Use the 31B dense model (from the previous post) as your heavy, deliberate Orchestrator / Verifier / Planner. Pass the actual execution tasks to this 26B MoE. At 160 t/s, this MoE can chew through code generation, tool calling, and massive RAG document retrieval over a 250k context window almost instantly, drastically speeding up your agentic loop. If you own a single RTX 3090 or 4090 and haven't tried this specific stack yet, you need to pull these latest updates and run it. Local inference just leveled up. Hugging Face links to the Unsloth 26B QAT quants and MTP drafters are in the replies. performance graphs also available in the replies.

40,993 次观看

my 8 GB VRAM gaming laptop is absolutely going to hate me for this. but I still did it. ran a 31b dense model (Gemma 4 31b Q4) with only 8 GB VRAM last week I ran Gemma 4 26B A4B a mixture of experts model on my RTX 4060 and hit 25–28 tokens/sec using llama.cpp's new MTP support. smooth. snappy. but MoE has a secret: it only activates 4B parameters per token despite having 26B total. that's why it flies. so the real question started haunting me. what if I throw a full, no tricks, every parameter fires on every token, 31B DENSE model at the same machine? # Hardware: GPU: NVIDIA RTX 4060, 8 GB VRAM RAM: 16 GB CPU: Intel Core i7 H Laptop. Gaming. Modest. The model: gemma-4-31B-it-qat-UD-Q4_K_XL.gguf (model's unsloth huggingface link in the comments) This is Google DeepMind's flagship dense model in the Gemma 4 family that can run on single consumer GPU. It packs a hybrid attention architecture, supports up to 256K context natively, and is QAT (Quantization Aware Training) optimized, meaning it retains far more quality than standard post training quants at the same bit depth. This is NOT the MoE. This is 31 BILLION dense parameters, every single one of them loaded. # the flags I used: -m gemma-4-31B-it-qat-UD-Q4_K_XL.gguf -cnv --spec-type draft-mtp --spec-draft-model mtp-gemma-4-31B-it.gguf --spec-draft-n-max 8 --spec-draft-p-min 0.6 -c 6000 -v Multi Token Prediction (MTP) is still active here. Separate draft GGUF required, same as the 26B setup. # Results: → Decode: ~3 tokens/sec → Prefill: ~2 tokens/sec → Context: 6000 tokens → Hardware crying quietly in the corner: yes so is 3 tps actually usable? For real time back and forth chat? Not ideal. You're not having a fluid conversation at 3 tps. but slow ≠ useless. And this is where it gets genuinely interesting. think about how senior devs actually work in a real team. But when something is architectural, deeply complex, or needs serious reasoning? they walk down the hall and escalate to the senior. That's exactly the local AI agent architecture this unlocks: → Fast orchestrator model (Gemma 4 26B MoE at 25+ tps) handles routing, simple queries, tool calls, memory. The junior dev. → Gemma 4 31B dense is the senior, called only when the fast model genuinely hits a wall. Hard multi step reasoning. Complex code generation. Deep architectural decisions. The agentic loop stays fast. Only the hard hops touch the 31B. That's a legitimate production grade local AI architecture on a budget hardware. (requires 2 8gb gpus) other workflows where 3 tps is completely fine: - overnight batch jobs. summarize documents, extract structured data, review code. Fire it off. Sleep. wake up to results. - One shot deep reasoning - Silent code audit loops, you write and test, the 31B reviews diffs and flags issues in the background between your sprints - Any workflow where output quality > output speed A few weeks ago, nobody was running a 30B+ dense model on a single consumer GPU with 8 GB VRAM. At all. Now we're doing it on an Intel i7-H gaming laptop with a NVIDIA RTX 4060, thanks to llama.cpp + QAT quants + MTP speculative drafting. Google DeepMind said the Gemma 4 31B targets "consumer GPUs and workstations." They were not exaggerating. The hardware bar to run serious frontier class models locally keeps dropping. the tools are here. the models are here. you just have to be willing to abuse your laptop a little. what workflows would you actually run on a local 3 tps 31B dense model? genuinely curious. drop it below.

my 8 GB VRAM gaming laptop is absolutely going to hate me for this. but I still did it. ran a 31b dense model (Gemma 4 31b Q4) with only 8 GB VRAM last week I ran Gemma 4 26B A4B a mixture of experts model on my RTX 4060 and hit 25–28 tokens/sec using llama.cpp's new MTP support. smooth. snappy. but MoE has a secret: it only activates 4B parameters per token despite having 26B total. that's why it flies. so the real question started haunting me. what if I throw a full, no tricks, every parameter fires on every token, 31B DENSE model at the same machine? # Hardware: GPU: NVIDIA RTX 4060, 8 GB VRAM RAM: 16 GB CPU: Intel Core i7 H Laptop. Gaming. Modest. The model: gemma-4-31B-it-qat-UD-Q4_K_XL.gguf (model's unsloth huggingface link in the comments) This is Google DeepMind's flagship dense model in the Gemma 4 family that can run on single consumer GPU. It packs a hybrid attention architecture, supports up to 256K context natively, and is QAT (Quantization Aware Training) optimized, meaning it retains far more quality than standard post training quants at the same bit depth. This is NOT the MoE. This is 31 BILLION dense parameters, every single one of them loaded. # the flags I used: -m gemma-4-31B-it-qat-UD-Q4_K_XL.gguf -cnv --spec-type draft-mtp --spec-draft-model mtp-gemma-4-31B-it.gguf --spec-draft-n-max 8 --spec-draft-p-min 0.6 -c 6000 -v Multi Token Prediction (MTP) is still active here. Separate draft GGUF required, same as the 26B setup. # Results: → Decode: ~3 tokens/sec → Prefill: ~2 tokens/sec → Context: 6000 tokens → Hardware crying quietly in the corner: yes so is 3 tps actually usable? For real time back and forth chat? Not ideal. You're not having a fluid conversation at 3 tps. but slow ≠ useless. And this is where it gets genuinely interesting. think about how senior devs actually work in a real team. But when something is architectural, deeply complex, or needs serious reasoning? they walk down the hall and escalate to the senior. That's exactly the local AI agent architecture this unlocks: → Fast orchestrator model (Gemma 4 26B MoE at 25+ tps) handles routing, simple queries, tool calls, memory. The junior dev. → Gemma 4 31B dense is the senior, called only when the fast model genuinely hits a wall. Hard multi step reasoning. Complex code generation. Deep architectural decisions. The agentic loop stays fast. Only the hard hops touch the 31B. That's a legitimate production grade local AI architecture on a budget hardware. (requires 2 8gb gpus) other workflows where 3 tps is completely fine: - overnight batch jobs. summarize documents, extract structured data, review code. Fire it off. Sleep. wake up to results. - One shot deep reasoning - Silent code audit loops, you write and test, the 31B reviews diffs and flags issues in the background between your sprints - Any workflow where output quality > output speed A few weeks ago, nobody was running a 30B+ dense model on a single consumer GPU with 8 GB VRAM. At all. Now we're doing it on an Intel i7-H gaming laptop with a NVIDIA RTX 4060, thanks to llama.cpp + QAT quants + MTP speculative drafting. Google DeepMind said the Gemma 4 31B targets "consumer GPUs and workstations." They were not exaggerating. The hardware bar to run serious frontier class models locally keeps dropping. the tools are here. the models are here. you just have to be willing to abuse your laptop a little. what workflows would you actually run on a local 3 tps 31B dense model? genuinely curious. drop it below.

63,689 次观看

The "I don't have enough VRAM" excuse just died. I’m running Meta’s new 30B Muse Glimmer Q6_K_XL with a massive 130k context window on just 26GB VRAM FREE compute on Kaggle. Kaggle provides you free 2x Nvidia T4 GPUs. 30 hours usage each week! Yesterday, I showed you the violent throughput of Muse Glimmer on a single RTX 4090. Today, we are securing a Dual NVIDIA T4 GPU cluster with 32GB of total VRAM for exactly $0 and dropping the massive 24.5GB Q6_K_XL GGUF onto it. Here is the exact Kaggle workflow and benchmarking breakdown: # 1. The Storage Bypass & Setup I built a clean cell by cell script in the file. We dynamically fetch the CUDA accelerated llama.cpp binaries and use wget to stream the model directly into Kaggle's /kaggle/tmp scratch storage, which cleanly bypasses their 19.5GB output directory limit. # 2. The Multi GPU Performance With the -ngl 99 flag offloading all model layers across both T4 GPUs (32GB VRAM combined), we pushed a massive 131,072 token context window (-c 131072). The benchmark numbers: Prefill: 265.9 t/s Decode: 9.0 t/s VRAM Total: 26.5 GB # 3. The Architecture Insight The Q6_K_XL model itself is 24.5 GB. Because of Muse Glimmer's aggressive 16:1 GQA, the unquantized KV cache for a massive 130k context window only takes up 2 GB of memory. No heavily degraded Q4 KV quantization required. It just works. No compiling from source. No credit card. No OOM crashes. Zero excuses. If you’re running a single RTX 3090, 4090, or 5090, you need to experience this hyper efficient KV cache right now before the upcoming Qwen 3.8 27B drop completely steals your VRAM tomorrow. pick the Q4 or Q5 quants for 24 GB VRAM rigs. I'm dropping the Unsloth huggingface GGUF links and the free Kaggle notebook link in the replies. spin up your own instance, and show me your multi GPU benchmarks.

The "I don't have enough VRAM" excuse just died. I’m running Meta’s new 30B Muse Glimmer Q6_K_XL with a massive 130k context window on just 26GB VRAM FREE compute on Kaggle. Kaggle provides you free 2x Nvidia T4 GPUs. 30 hours usage each week! Yesterday, I showed you the violent throughput of Muse Glimmer on a single RTX 4090. Today, we are securing a Dual NVIDIA T4 GPU cluster with 32GB of total VRAM for exactly $0 and dropping the massive 24.5GB Q6_K_XL GGUF onto it. Here is the exact Kaggle workflow and benchmarking breakdown: # 1. The Storage Bypass & Setup I built a clean cell by cell script in the file. We dynamically fetch the CUDA accelerated llama.cpp binaries and use wget to stream the model directly into Kaggle's /kaggle/tmp scratch storage, which cleanly bypasses their 19.5GB output directory limit. # 2. The Multi GPU Performance With the -ngl 99 flag offloading all model layers across both T4 GPUs (32GB VRAM combined), we pushed a massive 131,072 token context window (-c 131072). The benchmark numbers: Prefill: 265.9 t/s Decode: 9.0 t/s VRAM Total: 26.5 GB # 3. The Architecture Insight The Q6_K_XL model itself is 24.5 GB. Because of Muse Glimmer's aggressive 16:1 GQA, the unquantized KV cache for a massive 130k context window only takes up 2 GB of memory. No heavily degraded Q4 KV quantization required. It just works. No compiling from source. No credit card. No OOM crashes. Zero excuses. If you’re running a single RTX 3090, 4090, or 5090, you need to experience this hyper efficient KV cache right now before the upcoming Qwen 3.8 27B drop completely steals your VRAM tomorrow. pick the Q4 or Q5 quants for 24 GB VRAM rigs. I'm dropping the Unsloth huggingface GGUF links and the free Kaggle notebook link in the replies. spin up your own instance, and show me your multi GPU benchmarks.

19,370 次观看

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

you can just hallucinate the entire internet with Qwen 3.8 27b running at 2,000 tokens/second? part 2 of turning Cerebras + Qwen 3.8 27B into an OS: built an offline browser with zero network calls and mounted it directly the JIT ubuntu desktop. no wifi. no scraping. zero packets sent to external CDNs. you search a site, set a year, and qwen 27b at 1,950 tok/s synthesizes the entire DOM on the fly. here is youtube in 2045 vs 1999: → search google for youtube inside the OS → scrub to 2045: instant futuristic feed → scrub to 1999: raw web 1.0 time capsule in seconds at this speed, browsing isn't retrieving files from a server, it's querying an alternate reality. a 2D browser window is just step zero. imagine full operating systems, virtual worlds, and complex simulation engines existing purely as model weights. zero gigabytes stored on disk, just pure interactive reality streamed on demand. What else becomes a possibility with the qwen 3.8 27b (dense) at 2000 tokens/sec?
0:33
analogalok's profile picture

you can just hallucinate the entire internet with Qwen 3.8 27b running at 2,000 tokens/second? part 2 of turning Cerebras + Qwen 3.8 27B into an OS: built an offline browser with zero network calls and mounted it directly the JIT ubuntu desktop. no wifi. no scraping. zero packets sent to external CDNs. you search a site, set a year, and qwen 27b at 1,950 tok/s synthesizes the entire DOM on the fly. here is youtube in 2045 vs 1999: → search google for youtube inside the OS → scrub to 2045: instant futuristic feed → scrub to 1999: raw web 1.0 time capsule in seconds at this speed, browsing isn't retrieving files from a server, it's querying an alternate reality. a 2D browser window is just step zero. imagine full operating systems, virtual worlds, and complex simulation engines existing purely as model weights. zero gigabytes stored on disk, just pure interactive reality streamed on demand. What else becomes a possibility with the qwen 3.8 27b (dense) at 2000 tokens/sec?

Alok

867,704 次观看 • 1 天前

The VRAM barrier is officially dead. I just ran Qwen 3.8 Flash Next (MoE) 125B A6B with a 250,000 context window on a single 24GB RTX 4090. 21 tokens/sec decode. 364 t/s prefill. no mtp. no dflash. no kv cache quantization! We are running datacenter models on consumer hardware. Tested on Ubuntu 22 | CUDA 13.0 | PCIe 4.0 x16 | 110 GB DDR4 System RAM with a continuous 28k prompt across all runs. ### The Benchmarks & Scaling # 1. Hybrid Offload (-ncmoe 40 @ 80k Context) Offloaded 40 expert layers to the GPU, pushing VRAM to the ceiling. ./build/bin/llama-server -m Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf -c 80000 --port 8080 -v --fit off -b 4096 -ub 4096 -ncmoe 40 Prefill: 383.85 t/s | Decode: 22.52 t/s Footprint: 23.85 GB VRAM | 97 GB RAM # 2. Full CPU MoE Offload (-cmoe @ 80k Context) Pinned all 512 expert layers to DDR4 RAM (-cmoe), keeping attention on the 4090. llama.cpp flags: (Same as above, replace -ncmoe 40 with -cmoe) Prefill: 355.72 t/s | Decode: 20.84 t/s Footprint: 11.66 GB VRAM (12GB+ VRAM freed up!) | 110 GB RAM # 3. The 180,000 Context Run Prefill: 357.75 t/s | Decode: 20.98 t/s | VRAM: 15.6 GB | RAM: 110 GB # 4. The 250,000 Context Absolute Ceiling ./build/bin/llama-server -m Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf -c 250000 --port 8080 -v --fit off -b 4096 -ub 4096 -cmoe Prefill: 364.29 t/s | Decode: 20.97 t/s Footprint: 18.3 GB VRAM (Still ~5.7 GB of VRAM headroom!) | 110 GB RAM ### Key Insights: -b 4096 -ub 4096: doubles the prompt ingestion from ~150 to 364+ t/s. -cmoe Free Lunch: Shifting expert layers to DDR4 RAM slashes VRAM from 24GB to 11.6GB with virtually zero decode penalty (22.5 -> 20.9 t/s), enabling the 250k context ceiling. Qwen 3.8 Flash-Next (UD-Q4_K_XL) is a massive 111.4 GB model split across 4 shards. To run this architecture, you must build from the experimental PR branch (#27742) by Daniel Han: git clone && cd llama.cpp git fetch origin pull/27742/head:qwen-next && git checkout qwen-next cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=native -DBUILD_SHARED_LIBS=OFF cmake --build build --config Release -j $(nproc) --target llama-server A single 4090 paired with 100 GB of cheap DDR4 RAM will comfortably serve production grade 125B inference. While Qwen 3.8 27B (dense) still holds the crown for single 3090/4090 rigs, Flash Next proves 125B hybrid models are officially viable on consumer hardware. Hugging Face GGUF link and complete performance telemetry graphs are dropped in the replies below. GLM 5.3 Flash VS Qwen 3.8 Flash Next, which one takes the open weights crown this week?
0:20
analogalok's profile picture

The VRAM barrier is officially dead. I just ran Qwen 3.8 Flash Next (MoE) 125B A6B with a 250,000 context window on a single 24GB RTX 4090. 21 tokens/sec decode. 364 t/s prefill. no mtp. no dflash. no kv cache quantization! We are running datacenter models on consumer hardware. Tested on Ubuntu 22 | CUDA 13.0 | PCIe 4.0 x16 | 110 GB DDR4 System RAM with a continuous 28k prompt across all runs. ### The Benchmarks & Scaling # 1. Hybrid Offload (-ncmoe 40 @ 80k Context) Offloaded 40 expert layers to the GPU, pushing VRAM to the ceiling. ./build/bin/llama-server -m Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf -c 80000 --port 8080 -v --fit off -b 4096 -ub 4096 -ncmoe 40 Prefill: 383.85 t/s | Decode: 22.52 t/s Footprint: 23.85 GB VRAM | 97 GB RAM # 2. Full CPU MoE Offload (-cmoe @ 80k Context) Pinned all 512 expert layers to DDR4 RAM (-cmoe), keeping attention on the 4090. llama.cpp flags: (Same as above, replace -ncmoe 40 with -cmoe) Prefill: 355.72 t/s | Decode: 20.84 t/s Footprint: 11.66 GB VRAM (12GB+ VRAM freed up!) | 110 GB RAM # 3. The 180,000 Context Run Prefill: 357.75 t/s | Decode: 20.98 t/s | VRAM: 15.6 GB | RAM: 110 GB # 4. The 250,000 Context Absolute Ceiling ./build/bin/llama-server -m Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf -c 250000 --port 8080 -v --fit off -b 4096 -ub 4096 -cmoe Prefill: 364.29 t/s | Decode: 20.97 t/s Footprint: 18.3 GB VRAM (Still ~5.7 GB of VRAM headroom!) | 110 GB RAM ### Key Insights: -b 4096 -ub 4096: doubles the prompt ingestion from ~150 to 364+ t/s. -cmoe Free Lunch: Shifting expert layers to DDR4 RAM slashes VRAM from 24GB to 11.6GB with virtually zero decode penalty (22.5 -> 20.9 t/s), enabling the 250k context ceiling. Qwen 3.8 Flash-Next (UD-Q4_K_XL) is a massive 111.4 GB model split across 4 shards. To run this architecture, you must build from the experimental PR branch (#27742) by Daniel Han: git clone && cd llama.cpp git fetch origin pull/27742/head:qwen-next && git checkout qwen-next cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=native -DBUILD_SHARED_LIBS=OFF cmake --build build --config Release -j $(nproc) --target llama-server A single 4090 paired with 100 GB of cheap DDR4 RAM will comfortably serve production grade 125B inference. While Qwen 3.8 27B (dense) still holds the crown for single 3090/4090 rigs, Flash Next proves 125B hybrid models are officially viable on consumer hardware. Hugging Face GGUF link and complete performance telemetry graphs are dropped in the replies below. GLM 5.3 Flash VS Qwen 3.8 Flash Next, which one takes the open weights crown this week?

Alok

1,013,451 次观看 • 20 天前

Operating System powered by Qwen 3.8 27B at 1950 tokens/sec! here is what 1,950 tokens/second Qwen's 3.8 27b actually looks like on Cerebras: i wrote a minimal python web server that turns cerebras inference into a live operating system. zero apps on disk. when you double click an icon: 1) python proxies a raw SSE stream from qwen 27b at 1,950 tok/s 2) calculator compiles & mounts in 11s 3) full canvas paint studio with brush engine compiles in 10s. at 2,000 tokens/second, software is just an on demand hallucination that runs instantly. the model weights ARE the operating system runtime. what else would you build at 1,950 tokens/second?
1:00
analogalok's profile picture

Operating System powered by Qwen 3.8 27B at 1950 tokens/sec! here is what 1,950 tokens/second Qwen's 3.8 27b actually looks like on Cerebras: i wrote a minimal python web server that turns cerebras inference into a live operating system. zero apps on disk. when you double click an icon: 1) python proxies a raw SSE stream from qwen 27b at 1,950 tok/s 2) calculator compiles & mounts in 11s 3) full canvas paint studio with brush engine compiles in 10s. at 2,000 tokens/second, software is just an on demand hallucination that runs instantly. the model weights ARE the operating system runtime. what else would you build at 1,950 tokens/second?

Alok

64,189 次观看 • 3 天前

a new 8GB VRAM GPU dense Local LLM leader was born yesterday runs on: RTX 4060 / RTX 3070 / RTX 2080. any 8GB card Qwen 3.5 9B (dense) was the go to for 6-8GB VRAM builds. Gemma 4 12B QAT (dense) just changed that. same llama.cpp + cuda 13.2. i7 12700H. 16GB RAM. same -ngl 99 flags. same 48k context. unsloth gemma-4-12b-it-Q4_K_M.gguf → 15 tok/sec @ 48k ctx unsloth gemma-4-12B-it-qat-UD-Q4_K_XL.gguf → 32 tok/sec @ 48k ctx → 26 tok/sec @ 64k ctx 64k context is a big deal. Hermes 3 agent requires 64k minimum to run. you're now getting full hermes compatible context on a budget consumer GPU at 26 tok/sec locally. 2.1x faster on identical hardware. and here's the part that breaks your brain: the QAT-UD-Q4_K_XL is actually SMALLER than the Q4_K_M "XL" why? QAT = Quantization Aware Training Google didn't train the model first and compress it later they trained it to be quantized from day one the weights already know how to survive low precision that's why you get more quality per byte llamacpp flags: -m gemma-4-12B-it-qat-UD-Q4_K_XL.gguf -cnv -ngl 99 -c 48000 -v fits in 8GB VRAM clean. no API. no cloud. no subscription. and this isn't even the MTP variant yet Gemma-4-E2B QAT runs on 3GB RAM, E4B on 5GB, 12B on 7GB, 26-A4B on 15GB and 31B on 18GB. I have benchmarked the 26b and 31b qat as well on a single RTX 4090, checkout the comments for details. If you have a 6GB or 8GB VRAM GPU, post your numbers. more benchmarks and configs coming soon
0:22
analogalok's profile picture

a new 8GB VRAM GPU dense Local LLM leader was born yesterday runs on: RTX 4060 / RTX 3070 / RTX 2080. any 8GB card Qwen 3.5 9B (dense) was the go to for 6-8GB VRAM builds. Gemma 4 12B QAT (dense) just changed that. same llama.cpp + cuda 13.2. i7 12700H. 16GB RAM. same -ngl 99 flags. same 48k context. unsloth gemma-4-12b-it-Q4_K_M.gguf → 15 tok/sec @ 48k ctx unsloth gemma-4-12B-it-qat-UD-Q4_K_XL.gguf → 32 tok/sec @ 48k ctx → 26 tok/sec @ 64k ctx 64k context is a big deal. Hermes 3 agent requires 64k minimum to run. you're now getting full hermes compatible context on a budget consumer GPU at 26 tok/sec locally. 2.1x faster on identical hardware. and here's the part that breaks your brain: the QAT-UD-Q4_K_XL is actually SMALLER than the Q4_K_M "XL" why? QAT = Quantization Aware Training Google didn't train the model first and compress it later they trained it to be quantized from day one the weights already know how to survive low precision that's why you get more quality per byte llamacpp flags: -m gemma-4-12B-it-qat-UD-Q4_K_XL.gguf -cnv -ngl 99 -c 48000 -v fits in 8GB VRAM clean. no API. no cloud. no subscription. and this isn't even the MTP variant yet Gemma-4-E2B QAT runs on 3GB RAM, E4B on 5GB, 12B on 7GB, 26-A4B on 15GB and 31B on 18GB. I have benchmarked the 26b and 31b qat as well on a single RTX 4090, checkout the comments for details. If you have a 6GB or 8GB VRAM GPU, post your numbers. more benchmarks and configs coming soon

Alok

264,062 次观看 • 3 个月前

Google's Gemma 4 26B A4B QAT hits 25+ tokens/sec and 320+ tokens/sec prefill on 8 GB VRAM (RTX 4060) + 16 GB RAM using TurboQuant Prefill just went from 200 → 320+ tok/s on the same 8GB card. 1.6x, no new hardware, no new quant, just a KV cache trick stacked on top of the Gemma 4 26B MoE setup from a few days ago. A few days ago I posted Gemma 4 26B A4B hitting 28 tok/s decode on 8GB VRAM using native MTP. prefill was stuck around 200 tok/s. fair callout by the community. So today I tested something I'd already been meaning to try: TheTom/llama-cpp-turboquant, the TurboQuant KV cache fork by Tom Turney (Tom Turney). (github link in the comments) thanks to him, the fork just got resynced to mainline, so MTP + TurboQuant now run together cleanly (I didnt see any meaningful gains by using MTP with this setup though but you can try). The flags (No MTP): -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -cnv -c 64000 --cache-type-k q8_0 --cache-type-v turbo3 Results on the same RTX 4060 8GB, tested with a 27k token prompt at 64k context loaded: Prefill: 200 tok/s → 320+ tok/s Decode: stayed above 25 tok/s (without MTP) Why it works: TurboQuant uses walsh hadamard rotation + polar quantization on the KV cache. keys are sensitive to compression, values aren't much, so it splits the difference: K stays at q8_0, V drops to turbo3 (~3 bits). bonus from the memory savings: same 8GB card can now stretch to 100-120k context with minimal decode penalty. It should now be snappier with any agent harness such as hermes agent without compromise on intelligence. If you're already running Gemma 4 on a small card, this stacks on top for free. Try --cache-type-k q8_0 --cache-type-v turbo3 on your setup and report back what your prefill/decode split looks like. unsloth model gguf and llama.cpp turboquant fork links in the comments. what's your prefill number before vs after?
0:31
analogalok's profile picture

Google's Gemma 4 26B A4B QAT hits 25+ tokens/sec and 320+ tokens/sec prefill on 8 GB VRAM (RTX 4060) + 16 GB RAM using TurboQuant Prefill just went from 200 → 320+ tok/s on the same 8GB card. 1.6x, no new hardware, no new quant, just a KV cache trick stacked on top of the Gemma 4 26B MoE setup from a few days ago. A few days ago I posted Gemma 4 26B A4B hitting 28 tok/s decode on 8GB VRAM using native MTP. prefill was stuck around 200 tok/s. fair callout by the community. So today I tested something I'd already been meaning to try: TheTom/llama-cpp-turboquant, the TurboQuant KV cache fork by Tom Turney (Tom Turney). (github link in the comments) thanks to him, the fork just got resynced to mainline, so MTP + TurboQuant now run together cleanly (I didnt see any meaningful gains by using MTP with this setup though but you can try). The flags (No MTP): -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -cnv -c 64000 --cache-type-k q8_0 --cache-type-v turbo3 Results on the same RTX 4060 8GB, tested with a 27k token prompt at 64k context loaded: Prefill: 200 tok/s → 320+ tok/s Decode: stayed above 25 tok/s (without MTP) Why it works: TurboQuant uses walsh hadamard rotation + polar quantization on the KV cache. keys are sensitive to compression, values aren't much, so it splits the difference: K stays at q8_0, V drops to turbo3 (~3 bits). bonus from the memory savings: same 8GB card can now stretch to 100-120k context with minimal decode penalty. It should now be snappier with any agent harness such as hermes agent without compromise on intelligence. If you're already running Gemma 4 on a small card, this stacks on top for free. Try --cache-type-k q8_0 --cache-type-v turbo3 on your setup and report back what your prefill/decode split looks like. unsloth model gguf and llama.cpp turboquant fork links in the comments. what's your prefill number before vs after?

Alok

119,821 次观看 • 3 个月前

A single RTX 4090 (24 GB VRAM) can run the updated gemma 4 31B (dense) model with a 190,000 context window at 33 tokens/second. The VRAM barrier is dying. Google quietly updated Gemma 4, and Unsloth immediately compiled the new quants. I built llama.cpp from source on Ubuntu 22 to benchmark it. Google's stealth update 2 days ago enabled uniform Flash Attention 4 on Hopper to boost prefill and patched the chat template to improve tool calling. The agentic reasoning gains on the benchmark charts are massive: TB2 (Agents): +4.5% (to 25.8%) Tau2 (Telecom): +10.1% (to 62.7%) Running on Ubuntu 22, CUDA 13.0 with a single NVIDIA GeForce RTX 4090. Here is the exact step by step benchmarking process with a massive 28k tokens prompt and the commands I used to squeeze out maximum context without killing my throughput: # 1. The Baseline (Unquantized KV Cache) I started with full GPU offload (-ngl 99) and pushed the context to 40k. llama.cpp flags: ./build/bin/llama-server -m gemma-4-31B-it-qat-UD-Q4_K_XL.gguf -ngl 99 -c 40000 -fa on --port 8080 -v VRAM: 23.8 GB (maxed out on card) Throughput: Prefill: 2198.81 t/s | Decode: 35.77 t/s (with 28k tokens prompt) # 2. The CPU Split Trap I tried stretching to 80k context by offloading layers to the CPU (-ngl 52). llama.cpp flags: ./build/bin/llama-server -m gemma-4-31B-it-qat-UD-Q4_K_XL.gguf -c 80000 -ngl 52 -fa on --port 8080 -v Throughput: Prefill: 1212.73 t/s | Decode: 5 t/s (with 28k tokens prompt) # 3. The KV Quantization Breakthrough Instead of spilling layers to the CPU, I kept the model fully on card (-ngl 99) but enabled 8-bit KV cache quantization to free up VRAM. flags: ./build/bin/llama-server -m gemma-4-31B-it-qat-UD-Q4_K_XL.gguf -c 100000 --cache-type-k q8_0 --cache-type-v q8_0 -ngl 99 --port 8080 -v VRAM: 23.9 GB Throughput: Prefill: 2139.68 t/s | Decode: 32 t/s (with 28k tokens prompt) Result: 100k tokens of context on a single GPU with practically zero speed loss (and minimal intelligence loss). # 4. The Limit Test (Q4 KV Cache) To find the absolute breaking point, I dropped the KV cache to 4 bit (q4_0) and set -c 190000. flags: ./build/bin/llama-server -m gemma-4-31B-it-qat-UD-Q4_K_XL.gguf -c 190000 --cache-type-k q4_0 --cache-type-v q4_0 -ngl 99 --port 8080 -v VRAM: 23.8 GB Throughput: Prefill: 2206.66 t/s | Decode: 33 t/s (with 28k tokens prompt) (Note: Pushing it to 220k required dropping to -ngl 58 again, which immediately penalized decode down to 17 t/s). # The Tradeoff: For Max Reasoning: Keep your KV cache unquantized (f16). You get pristine reasoning but hit a strict 40k context ceiling. For Massive Document Retrieval: If you need to feed the model giant codebases, use --cache-type-k q4_0. Getting 190k context at 33 tokens/second on a consumer desktop with a 31b dense model is a cheat code. If you’re rocking a single 3090 or 4090 and slept on Gemma 4 earlier, this update is your cue to dust off the terminal. Hugging Face links to the Unsloth QAT quants are in the replies below.
0:20
analogalok's profile picture

A single RTX 4090 (24 GB VRAM) can run the updated gemma 4 31B (dense) model with a 190,000 context window at 33 tokens/second. The VRAM barrier is dying. Google quietly updated Gemma 4, and Unsloth immediately compiled the new quants. I built llama.cpp from source on Ubuntu 22 to benchmark it. Google's stealth update 2 days ago enabled uniform Flash Attention 4 on Hopper to boost prefill and patched the chat template to improve tool calling. The agentic reasoning gains on the benchmark charts are massive: TB2 (Agents): +4.5% (to 25.8%) Tau2 (Telecom): +10.1% (to 62.7%) Running on Ubuntu 22, CUDA 13.0 with a single NVIDIA GeForce RTX 4090. Here is the exact step by step benchmarking process with a massive 28k tokens prompt and the commands I used to squeeze out maximum context without killing my throughput: # 1. The Baseline (Unquantized KV Cache) I started with full GPU offload (-ngl 99) and pushed the context to 40k. llama.cpp flags: ./build/bin/llama-server -m gemma-4-31B-it-qat-UD-Q4_K_XL.gguf -ngl 99 -c 40000 -fa on --port 8080 -v VRAM: 23.8 GB (maxed out on card) Throughput: Prefill: 2198.81 t/s | Decode: 35.77 t/s (with 28k tokens prompt) # 2. The CPU Split Trap I tried stretching to 80k context by offloading layers to the CPU (-ngl 52). llama.cpp flags: ./build/bin/llama-server -m gemma-4-31B-it-qat-UD-Q4_K_XL.gguf -c 80000 -ngl 52 -fa on --port 8080 -v Throughput: Prefill: 1212.73 t/s | Decode: 5 t/s (with 28k tokens prompt) # 3. The KV Quantization Breakthrough Instead of spilling layers to the CPU, I kept the model fully on card (-ngl 99) but enabled 8-bit KV cache quantization to free up VRAM. flags: ./build/bin/llama-server -m gemma-4-31B-it-qat-UD-Q4_K_XL.gguf -c 100000 --cache-type-k q8_0 --cache-type-v q8_0 -ngl 99 --port 8080 -v VRAM: 23.9 GB Throughput: Prefill: 2139.68 t/s | Decode: 32 t/s (with 28k tokens prompt) Result: 100k tokens of context on a single GPU with practically zero speed loss (and minimal intelligence loss). # 4. The Limit Test (Q4 KV Cache) To find the absolute breaking point, I dropped the KV cache to 4 bit (q4_0) and set -c 190000. flags: ./build/bin/llama-server -m gemma-4-31B-it-qat-UD-Q4_K_XL.gguf -c 190000 --cache-type-k q4_0 --cache-type-v q4_0 -ngl 99 --port 8080 -v VRAM: 23.8 GB Throughput: Prefill: 2206.66 t/s | Decode: 33 t/s (with 28k tokens prompt) (Note: Pushing it to 220k required dropping to -ngl 58 again, which immediately penalized decode down to 17 t/s). # The Tradeoff: For Max Reasoning: Keep your KV cache unquantized (f16). You get pristine reasoning but hit a strict 40k context ceiling. For Massive Document Retrieval: If you need to feed the model giant codebases, use --cache-type-k q4_0. Getting 190k context at 33 tokens/second on a consumer desktop with a 31b dense model is a cheat code. If you’re rocking a single 3090 or 4090 and slept on Gemma 4 earlier, this update is your cue to dust off the terminal. Hugging Face links to the Unsloth QAT quants are in the replies below.

Alok

76,069 次观看 • 2 个月前

Deepseek V4 Flash 0731 (Q2) - 12 tokens/sec - Single RTX 4090 - 650+ tokens/sec prefill - 250k context - no kv cache quantization! DeepSeek just dropped the official V4 Flash 0731 two days ago with a massive agent capabilities upgrade. The official benchmarks are literally crushing their own V4-Pro-Preview on agentic tasks like Terminal Bench 2.1 and DeepSWE. Unsloth AI said they couldn't wait to bring it to local devices, and they delivered. If you thought my 118B Poolside Laguna S 2.1 MoE run last week on a single GPU was wild, hold onto your hardware. I just successfully ran Unsloth’s brand new 91GB DeepSeek-V4-Flash-0731 (UD-IQ2_M) GGUF entirely locally. And I pushed it to a mind-bending 250,000 context window. The VRAM ceiling is an illusion if you know how to optimize llama.cpp. Here are the benchmarks and the cheat codes to run a local frontier class model yourself. For the hardware and setup, I used a single NVIDIA RTX 4090 (24GB VRAM) hooked up via a PCIe 4 bus, running Ubuntu 22.04 LTS and CUDA 13.0. You don't need a massive enterprise server for this, if you have more than 80 GB of standard DDR4 RAM and a 24GB card like an RTX 3090 or 4090, you can run this exact stack yourself. All benchmarks were run using a massive 28k token prompt to truly stress test the prefill limits. no kv cache quantization THE BENCHMARKS (Scaling Context): # 80k Context (Baseline: -b 2048 -ub 2048): Prefill: 465.43 t/s | Decode: 13.00 t/s | VRAM: 22.87 GB # 80k Context (Optimized: -b 4096 -ub 4096): Prefill: 643.15 t/s | Decode: 12.20 t/s | VRAM: 23.00 GB (Notice how doubling the batch flags spiked my prefill throughput by nearly 200 t/s with almost zero VRAM penalty) # 180k Context (-b 4096 -ub 4096): Prefill: 629.18 t/s | Decode: 11.92 t/s | VRAM: 23.40 GB # 250k Context MAXIMUM (-b 4096 -ub 4096): Prefill: 619.02 t/s | Decode: 11.54 t/s | VRAM: 23.40 GB # THE SECRET SAUCE (Why this works): Unsloth’s UD-IQ2_M quant is ~91GB across 3 files. Since I only have 24GB of VRAM, the PCIe 4 bus and system RAM have to do the heavy lifting. The magic bullet is the --no-mmap flag. By completely bypassing OS disk paging, I forced llama.cpp to load the massive model weights directly into the system RAM upfront. Combined with Flash Attention (-fa on) and exactly 12 CPU threads (--threads 12), I maintained an incredibly stable 11.5+ tokens/sec decode speed even at a quarter million token context. # THE EXACT COMMAND: ./build/bin/llama-server -m /workspace/models/DeepSeek-V4-Flash-0731-UD-IQ2_M-00001-of-00003.gguf -c 250000 -fa on --port 8080 --threads 12 -b 4096 -ub 4096 --no-mmap -v Local conversational and agentic coding AI is fully here. You don’t need an API or an H100 cluster. Qwen 3.8 27b drops next week making the 24GB VRAM tier even more worthwhile. What does your current local AI rig look like, and what's the craziest model you've managed to squeeze into it? Official huggingface GGUF links from Unsloth and performance graphs are dropped in the replies below!
0:21
analogalok's profile picture

Deepseek V4 Flash 0731 (Q2) - 12 tokens/sec - Single RTX 4090 - 650+ tokens/sec prefill - 250k context - no kv cache quantization! DeepSeek just dropped the official V4 Flash 0731 two days ago with a massive agent capabilities upgrade. The official benchmarks are literally crushing their own V4-Pro-Preview on agentic tasks like Terminal Bench 2.1 and DeepSWE. Unsloth AI said they couldn't wait to bring it to local devices, and they delivered. If you thought my 118B Poolside Laguna S 2.1 MoE run last week on a single GPU was wild, hold onto your hardware. I just successfully ran Unsloth’s brand new 91GB DeepSeek-V4-Flash-0731 (UD-IQ2_M) GGUF entirely locally. And I pushed it to a mind-bending 250,000 context window. The VRAM ceiling is an illusion if you know how to optimize llama.cpp. Here are the benchmarks and the cheat codes to run a local frontier class model yourself. For the hardware and setup, I used a single NVIDIA RTX 4090 (24GB VRAM) hooked up via a PCIe 4 bus, running Ubuntu 22.04 LTS and CUDA 13.0. You don't need a massive enterprise server for this, if you have more than 80 GB of standard DDR4 RAM and a 24GB card like an RTX 3090 or 4090, you can run this exact stack yourself. All benchmarks were run using a massive 28k token prompt to truly stress test the prefill limits. no kv cache quantization THE BENCHMARKS (Scaling Context): # 80k Context (Baseline: -b 2048 -ub 2048): Prefill: 465.43 t/s | Decode: 13.00 t/s | VRAM: 22.87 GB # 80k Context (Optimized: -b 4096 -ub 4096): Prefill: 643.15 t/s | Decode: 12.20 t/s | VRAM: 23.00 GB (Notice how doubling the batch flags spiked my prefill throughput by nearly 200 t/s with almost zero VRAM penalty) # 180k Context (-b 4096 -ub 4096): Prefill: 629.18 t/s | Decode: 11.92 t/s | VRAM: 23.40 GB # 250k Context MAXIMUM (-b 4096 -ub 4096): Prefill: 619.02 t/s | Decode: 11.54 t/s | VRAM: 23.40 GB # THE SECRET SAUCE (Why this works): Unsloth’s UD-IQ2_M quant is ~91GB across 3 files. Since I only have 24GB of VRAM, the PCIe 4 bus and system RAM have to do the heavy lifting. The magic bullet is the --no-mmap flag. By completely bypassing OS disk paging, I forced llama.cpp to load the massive model weights directly into the system RAM upfront. Combined with Flash Attention (-fa on) and exactly 12 CPU threads (--threads 12), I maintained an incredibly stable 11.5+ tokens/sec decode speed even at a quarter million token context. # THE EXACT COMMAND: ./build/bin/llama-server -m /workspace/models/DeepSeek-V4-Flash-0731-UD-IQ2_M-00001-of-00003.gguf -c 250000 -fa on --port 8080 --threads 12 -b 4096 -ub 4096 --no-mmap -v Local conversational and agentic coding AI is fully here. You don’t need an API or an H100 cluster. Qwen 3.8 27b drops next week making the 24GB VRAM tier even more worthwhile. What does your current local AI rig look like, and what's the craziest model you've managed to squeeze into it? Official huggingface GGUF links from Unsloth and performance graphs are dropped in the replies below!

Alok

46,100 次观看 • 1 个月前

six months ago this wasn't happening on 8gb vram. running unsloth's Q4_K_XL quant of gemma 4 26b-a4b-it-qat, a sparse MoE model with only 4b active params on a single rtx 4060 laptop gpu, 8gb vram, 20+ tok/s decode. no cloud, no api, no offload hacks. just a gaming laptop on battery. what makes it fit: google's QAT (quantization aware training), plus MTP (multi token prediction) support in the latest llama.cpp builds. that combo is the single biggest unlock for local inference on low vram. rtx 3060, rtx 3070, gtx 1070, gtx 1080, rtx 4050, rtx 4060, rtx 5050, rtx 5060 — any 6-8gb consumer gpu, old or new — this model runs on it. world cup season, so i told it to build a soccer themed flappy bird clone. one shot, zero iteration, fully playable. six months ago an 8gb model could barely clone vanilla flappy bird. now it's shipping a themed game from a sparse MoE model running locally on a laptop battery. inference benchmarks: - decode throughput: 30 tok/s - context: 64k. this is the real unlock. 64k ctx is what makes a hermes agent loop viable locally on this model, not just single-turn chat. llama.cpp flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 64000 -cmoe --port 8080 game's deployed on my own site, built and shipped end to end with open source llm, zero closed source api dependency in the pipeline. link in the description. gguf weights on huggingface, link in the comments. pull it down, run it on whatever 8gb card is sitting in your rig. try the game and tell me your score and what you want in v2. local llms on consumer gpus stopped being a meme.
0:20
analogalok's profile picture

six months ago this wasn't happening on 8gb vram. running unsloth's Q4_K_XL quant of gemma 4 26b-a4b-it-qat, a sparse MoE model with only 4b active params on a single rtx 4060 laptop gpu, 8gb vram, 20+ tok/s decode. no cloud, no api, no offload hacks. just a gaming laptop on battery. what makes it fit: google's QAT (quantization aware training), plus MTP (multi token prediction) support in the latest llama.cpp builds. that combo is the single biggest unlock for local inference on low vram. rtx 3060, rtx 3070, gtx 1070, gtx 1080, rtx 4050, rtx 4060, rtx 5050, rtx 5060 — any 6-8gb consumer gpu, old or new — this model runs on it. world cup season, so i told it to build a soccer themed flappy bird clone. one shot, zero iteration, fully playable. six months ago an 8gb model could barely clone vanilla flappy bird. now it's shipping a themed game from a sparse MoE model running locally on a laptop battery. inference benchmarks: - decode throughput: 30 tok/s - context: 64k. this is the real unlock. 64k ctx is what makes a hermes agent loop viable locally on this model, not just single-turn chat. llama.cpp flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 64000 -cmoe --port 8080 game's deployed on my own site, built and shipped end to end with open source llm, zero closed source api dependency in the pipeline. link in the description. gguf weights on huggingface, link in the comments. pull it down, run it on whatever 8gb card is sitting in your rig. try the game and tell me your score and what you want in v2. local llms on consumer gpus stopped being a meme.

Alok

61,660 次观看 • 2 个月前

I freaked out when my WiFi router suddenly died. then realized my autonomous Hermes agent is running fully local, nothing stopped. Hermes Agent + Gemma 4 26B A4B QAT MoE, 100% local on my laptop, building my side projects while I scroll my phone zero API calls. zero cost. 100% private. fully offline. This might be the most satisfying thing I’ve watched in a while. last post: showed Hermes + local Gemma 4 26B pull off backtest a trading strategy. this time I asked it to develop something i'd use myself everyday: # A full unpacked extension with: - React side panel UI - Local llama.cpp backend (offline AI) - Live tab sync + status tracking - Auto context extraction via Readability.js Vision on Demand → captures viewport screenshots as compressed JPEGs Deterministic action system -> model outputs tokens -> directly controls page scrolling It planned everything first. Then started executing step by step. all i did was say 'ok'. only once. # What’s wild: - It reports back after every phase - Auto compresses context when nearing limits - Actualy, stays on track llama.cpp flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 64000 --cache-type-k q8_0 --cache-type-v q8_0 --port 8080 # Performance on a single NVIDIA RTX 4060 (8GB VRAM) + 16 GB DDR4 RAM Gaming Laptop: - 300 tokens/sec prefill - 25+ tokens/sec decode More than usable for real dev workflows. This isn’t AI demo territory anymore. This is autonomous local software actually building things.
0:26
analogalok's profile picture

I freaked out when my WiFi router suddenly died. then realized my autonomous Hermes agent is running fully local, nothing stopped. Hermes Agent + Gemma 4 26B A4B QAT MoE, 100% local on my laptop, building my side projects while I scroll my phone zero API calls. zero cost. 100% private. fully offline. This might be the most satisfying thing I’ve watched in a while. last post: showed Hermes + local Gemma 4 26B pull off backtest a trading strategy. this time I asked it to develop something i'd use myself everyday: # A full unpacked extension with: - React side panel UI - Local llama.cpp backend (offline AI) - Live tab sync + status tracking - Auto context extraction via Readability.js Vision on Demand → captures viewport screenshots as compressed JPEGs Deterministic action system -> model outputs tokens -> directly controls page scrolling It planned everything first. Then started executing step by step. all i did was say 'ok'. only once. # What’s wild: - It reports back after every phase - Auto compresses context when nearing limits - Actualy, stays on track llama.cpp flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 64000 --cache-type-k q8_0 --cache-type-v q8_0 --port 8080 # Performance on a single NVIDIA RTX 4060 (8GB VRAM) + 16 GB DDR4 RAM Gaming Laptop: - 300 tokens/sec prefill - 25+ tokens/sec decode More than usable for real dev workflows. This isn’t AI demo territory anymore. This is autonomous local software actually building things.

Alok

56,428 次观看 • 2 个月前

I just crammed the updated Gemma 4 26B A4B QAT (MoE) with 180k context into an 8GB RTX 4060 (8 GB VRAM + 16 GB RAM only!!) and optimized the batch size. 23 tokens/sec decode, 300 tokens/sec prefill Yesterday I showed you a Gemma 4 31B dense model running flawlessly on an RTX 4090. Today, we're breaking the VRAM bank on a budget card using Unsloth’s new Gemma 4 26B (A4B) QAT quants. Following Google’s chat template update that boosted agentic benchmarks by +10%, I pushed this model to its absolute limits. Here is how you squeeze 250k context out of 8GB of VRAM. # The Setup & The Optimization - Hardware: Nvidia RTX 4060 (8GB VRAM) + 16GB System RAM - Environment: CUDA 13.0 build of llama.cpp - Model: gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf - Prompt: 28,000 tokens of prompt for each run If you read my L2 cache breakdown (attached in replies), you know the 4060’s 24MB cache maxes out at `-b 1024 -ub 1024`. Push past that, and prefill crashes. I locked those flags in for every test below to ensure maximum GEMM throughput. # 1. The Raw Context Push (Unquantized KV Cache) First, I wanted to see how far pure 8GB VRAM + 16GB RAM could stretch without touching the KV cache: - 80k Context: Prefill 385 t/s | Decode 25.5 t/s - 120k Context: Prefill 270 t/s | Decode 24 t/s llama.cpp flags: .\llama-server -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 120000 --port 8080 -ub 1024 -b 1024 Without KV quantization, 120k is your hard ceiling. push past that prefill throughput drops off a cliff, making the model practically unusable for large agentic workloads. # 2. The Q8 KV Cache Lifeline To survive 250k context on a budget card, you have to quantize the KV cache. I enabled 8 bit KV cache (`-ctk q8_0 -ctv q8_0`) and re ran: - 180k Context: Prefill 280 t/s | Decode 22.8 t/s - 250k Context: Prefill 115 t/s | Decode 20 t/s llama.cpp flags: .\llama-server -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 180000 --port 8080 -b 1024 -ub 1024 -ctk q8_0 -ctv q8_0 Result: Q8 KV cache brings 250k context back from the dead. Decode speed stabilizes at a highly usable 20 t/s. You are trading a very small bit amount of reasoning precision for an extra 130,000 tokens of context window. if you own a single rtx 3050, 3060, 3070, 4050, 4060, 5050 or 5060, you must try this model and optimize your batch size for higher prefill. Hugging Face links to the updated Unsloth's QAT quants and performance graph are in the replies below. What model are you running on your 6GB, 8GB or 12GB cards right now? Let's see your setups.
0:20
analogalok's profile picture

I just crammed the updated Gemma 4 26B A4B QAT (MoE) with 180k context into an 8GB RTX 4060 (8 GB VRAM + 16 GB RAM only!!) and optimized the batch size. 23 tokens/sec decode, 300 tokens/sec prefill Yesterday I showed you a Gemma 4 31B dense model running flawlessly on an RTX 4090. Today, we're breaking the VRAM bank on a budget card using Unsloth’s new Gemma 4 26B (A4B) QAT quants. Following Google’s chat template update that boosted agentic benchmarks by +10%, I pushed this model to its absolute limits. Here is how you squeeze 250k context out of 8GB of VRAM. # The Setup & The Optimization - Hardware: Nvidia RTX 4060 (8GB VRAM) + 16GB System RAM - Environment: CUDA 13.0 build of llama.cpp - Model: gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf - Prompt: 28,000 tokens of prompt for each run If you read my L2 cache breakdown (attached in replies), you know the 4060’s 24MB cache maxes out at `-b 1024 -ub 1024`. Push past that, and prefill crashes. I locked those flags in for every test below to ensure maximum GEMM throughput. # 1. The Raw Context Push (Unquantized KV Cache) First, I wanted to see how far pure 8GB VRAM + 16GB RAM could stretch without touching the KV cache: - 80k Context: Prefill 385 t/s | Decode 25.5 t/s - 120k Context: Prefill 270 t/s | Decode 24 t/s llama.cpp flags: .\llama-server -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 120000 --port 8080 -ub 1024 -b 1024 Without KV quantization, 120k is your hard ceiling. push past that prefill throughput drops off a cliff, making the model practically unusable for large agentic workloads. # 2. The Q8 KV Cache Lifeline To survive 250k context on a budget card, you have to quantize the KV cache. I enabled 8 bit KV cache (`-ctk q8_0 -ctv q8_0`) and re ran: - 180k Context: Prefill 280 t/s | Decode 22.8 t/s - 250k Context: Prefill 115 t/s | Decode 20 t/s llama.cpp flags: .\llama-server -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 180000 --port 8080 -b 1024 -ub 1024 -ctk q8_0 -ctv q8_0 Result: Q8 KV cache brings 250k context back from the dead. Decode speed stabilizes at a highly usable 20 t/s. You are trading a very small bit amount of reasoning precision for an extra 130,000 tokens of context window. if you own a single rtx 3050, 3060, 3070, 4050, 4060, 5050 or 5060, you must try this model and optimize your batch size for higher prefill. Hugging Face links to the updated Unsloth's QAT quants and performance graph are in the replies below. What model are you running on your 6GB, 8GB or 12GB cards right now? Let's see your setups.

Alok

36,617 次观看 • 1 个月前

Auto regressive LLMs are officially on notice. run Gemma 4 26B diffusion gguf with llama.cpp Google just dropped DiffusionGemma-26B, and it completely flips how we generate text. instead of predicting words one by one, it generates 256 tokens in parallel using bi-directional attention. its like stable diffusion, but for language. the model starts with random text "noise" and iteratively refines and self-corrects the entire block in real-time to fix formatting and reasoning errors on the fly. since it’s a Mixture of Experts (MoE) that only activates 3.8B parameters during inference, it fits perfectly on consumer hardware. You can run the Q4_K_M quant with an 18GB VRAM budget on a single RTX 3090 or RTX 4090 with exceptional throughput. Tested on Ubuntu 22 with CUDA 13.1 using the cutting edge experimental llama.cpp branch. Here is how to compile and run it with the live terminal denoising visualizer: # 1. Clone & check out the experimental PR (#24423) - 1) git clone && cd llama.cpp -git fetch origin 2) pull/24423/head:diffusiongemma && --git checkout diffusiongemma # 2. Build with CUDA support 1) cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=native 2) cmake --build build -j $(nproc) --config Release --target llama-diffusion-cli # 3. Run with live visual denoising (llama.cpp flags) ./build/bin/llama-diffusion-cli \ -m /path/to/diffusiongemma-26B-A4B-it-Q4_K_M.gguf \ -ngl 99 -cnv -n 2048 --diffusion-visual Watch the video below to see the live --diffusion-visual canvas iteratively de noising the prompt output in real time. guide and unsloth's hugging face GGUF model links are in the comments below! Is auto regressive generation officially legacy tech? Let me know what you think.
0:31
analogalok's profile picture

Auto regressive LLMs are officially on notice. run Gemma 4 26B diffusion gguf with llama.cpp Google just dropped DiffusionGemma-26B, and it completely flips how we generate text. instead of predicting words one by one, it generates 256 tokens in parallel using bi-directional attention. its like stable diffusion, but for language. the model starts with random text "noise" and iteratively refines and self-corrects the entire block in real-time to fix formatting and reasoning errors on the fly. since it’s a Mixture of Experts (MoE) that only activates 3.8B parameters during inference, it fits perfectly on consumer hardware. You can run the Q4_K_M quant with an 18GB VRAM budget on a single RTX 3090 or RTX 4090 with exceptional throughput. Tested on Ubuntu 22 with CUDA 13.1 using the cutting edge experimental llama.cpp branch. Here is how to compile and run it with the live terminal denoising visualizer: # 1. Clone & check out the experimental PR (#24423) - 1) git clone && cd llama.cpp -git fetch origin 2) pull/24423/head:diffusiongemma && --git checkout diffusiongemma # 2. Build with CUDA support 1) cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=native 2) cmake --build build -j $(nproc) --config Release --target llama-diffusion-cli # 3. Run with live visual denoising (llama.cpp flags) ./build/bin/llama-diffusion-cli \ -m /path/to/diffusiongemma-26B-A4B-it-Q4_K_M.gguf \ -ngl 99 -cnv -n 2048 --diffusion-visual Watch the video below to see the live --diffusion-visual canvas iteratively de noising the prompt output in real time. guide and unsloth's hugging face GGUF model links are in the comments below! Is auto regressive generation officially legacy tech? Let me know what you think.

Alok

52,656 次观看 • 3 个月前

If you are running local LLMs without N-gram speculative decoding, you are wasting massive amounts of compute. Whether your AI is editing a document, outputting structured JSON, or rewriting boilerplate templates, a huge chunk of the text it generates is highly repetitive or already exists right there in the prompt. Standard decoding wastes expensive GPU compute cycles "re thinking" every single token. By adding one hidden flag in llama.cpp, you can instantly fast forward through the repetition. Zero draft models. Zero extra VRAM. And virtually zero compute overhead. Google Colab hands you an enterprise grade NVIDIA Tesla T4 GPU with 16GB of VRAM for free. It’s the perfect Ubuntu Linux sandbox to build a bleeding edge inference engine from scratch. Recently, I showed you how to double your local speeds using MTP (Multi Token Prediction). But MTP requires a secondary neural network draft model. That eats into your precious VRAM (slightly though) and burns extra compute for every guess it makes. N-gram Speculative Decoding gives you a massive speed boost for exactly 0 memory cost and minimal compute. And it's faster than MTP when it works. Here is how it actually works under the hood: Standard autoregressive decoding is slow because it predicts one token at a time. If you ask an agent to format a long JSON object or update one line in an HTML file, it runs heavy matrix multiplications to calculate the probability of every single bracket, space, and letter from scratch. N-gram changes the game. It acts as a lightweight caching system. Instead of running heavy neural network math to guess the next word, it uses a simple hash table. Whenever the LLM starts outputting a sequence of tokens that already exists anywhere in its context window, N-gram instantly recognizes the pattern. Because it is just doing lightning fast string matching, the compute cost is practically zero. It "fast forwards" through the text, drafting the boilerplate instantly from memory, and the main model just verifies it in parallel. Pure speed. Using quantized GGUFs from Unsloth via HuggingFace, I spun up DeepMind’s massive Gemma 4 26B A4B QAT MoE on a free Colab instance to test this. Just look at the raw benchmark data on code editing task: Without N-gram: [ Prompt: 638.6 t/s | Generation: 45.9 t/s ] With N-gram: [ Prompt: 601.9 t/s | Generation: 107.1 t/s ] Here is the exact llama.cpp CLI command to activate it. Notice we don't even need the --model-draft flag: ./llama-cli -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -cnv -n 6000 -c 12000 -ngl 99 -fa on --spec-type ngram-mod Stop waiting for your GPU to re calculate words it already knows. I’ve built a free, interactive, cell by cell Google Colab notebook that lets you test this live in your browser. You can literally chat with the model and watch the text generation speed absolutely fly on the second turn when you ask it to edit a file. There are additional parameters for ngram-mod that you can tune once you get it working with the single flag. Link to the free Colab Notebook is in the comments below. It walks you through the entire stack: pulling pre built llama.cpp CUDA binaries for Linux, fetching GGUFs from HuggingFace, and spinning up the inference engine with ngram-mod from scratch. Let me know if you have already tried ngram-mod
0:23
analogalok's profile picture

If you are running local LLMs without N-gram speculative decoding, you are wasting massive amounts of compute. Whether your AI is editing a document, outputting structured JSON, or rewriting boilerplate templates, a huge chunk of the text it generates is highly repetitive or already exists right there in the prompt. Standard decoding wastes expensive GPU compute cycles "re thinking" every single token. By adding one hidden flag in llama.cpp, you can instantly fast forward through the repetition. Zero draft models. Zero extra VRAM. And virtually zero compute overhead. Google Colab hands you an enterprise grade NVIDIA Tesla T4 GPU with 16GB of VRAM for free. It’s the perfect Ubuntu Linux sandbox to build a bleeding edge inference engine from scratch. Recently, I showed you how to double your local speeds using MTP (Multi Token Prediction). But MTP requires a secondary neural network draft model. That eats into your precious VRAM (slightly though) and burns extra compute for every guess it makes. N-gram Speculative Decoding gives you a massive speed boost for exactly 0 memory cost and minimal compute. And it's faster than MTP when it works. Here is how it actually works under the hood: Standard autoregressive decoding is slow because it predicts one token at a time. If you ask an agent to format a long JSON object or update one line in an HTML file, it runs heavy matrix multiplications to calculate the probability of every single bracket, space, and letter from scratch. N-gram changes the game. It acts as a lightweight caching system. Instead of running heavy neural network math to guess the next word, it uses a simple hash table. Whenever the LLM starts outputting a sequence of tokens that already exists anywhere in its context window, N-gram instantly recognizes the pattern. Because it is just doing lightning fast string matching, the compute cost is practically zero. It "fast forwards" through the text, drafting the boilerplate instantly from memory, and the main model just verifies it in parallel. Pure speed. Using quantized GGUFs from Unsloth via HuggingFace, I spun up DeepMind’s massive Gemma 4 26B A4B QAT MoE on a free Colab instance to test this. Just look at the raw benchmark data on code editing task: Without N-gram: [ Prompt: 638.6 t/s | Generation: 45.9 t/s ] With N-gram: [ Prompt: 601.9 t/s | Generation: 107.1 t/s ] Here is the exact llama.cpp CLI command to activate it. Notice we don't even need the --model-draft flag: ./llama-cli -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -cnv -n 6000 -c 12000 -ngl 99 -fa on --spec-type ngram-mod Stop waiting for your GPU to re calculate words it already knows. I’ve built a free, interactive, cell by cell Google Colab notebook that lets you test this live in your browser. You can literally chat with the model and watch the text generation speed absolutely fly on the second turn when you ask it to edit a file. There are additional parameters for ngram-mod that you can tune once you get it working with the single flag. Link to the free Colab Notebook is in the comments below. It walks you through the entire stack: pulling pre built llama.cpp CUDA binaries for Linux, fetching GGUFs from HuggingFace, and spinning up the inference engine with ngram-mod from scratch. Let me know if you have already tried ngram-mod

Alok

31,765 次观看 • 2 个月前

Gemma 4 12B QAT + MTP on 8GB VRAM. llama.cpp flags included. let's run it. 20+ tok/sec decode. 700+ tok/sec prefill. on a single RTX 4060. copy these exact flags: -m gemma-4-12B-it-qat-UD-Q4_K_XL.gguf \ --spec-type draft-mtp \ --spec-draft-n-max 4 \ --spec-draft-p-min 0.7 \ --spec-draft-model gemma-4-12B-it-qat-assistant-MTP-Q8_0.gguf \ -c 48000 -ngl 38 -v → -ngl 99 if you're on 12–24GB VRAM (RTX 3090, 4090, 4080, 3080, 4070 Ti, 3080 Ti) → -ngl 38 for 8GB setups with 48k context (RTX 4060, 3060, 2080, 2070, 3070) → drop it (or the context) lower if you're squeezing on 4–6GB (RTX 2060, 3050, 1660) my rig: RTX 4060 8GB · i7H · 16GB RAM MTP is giving me 25–40% decode throughput gains across Gemma 4 models. nearly zero VRAM cost for that bump. the draft assistant GGUF is only ~300–400MB depending on quant. one thing to know (architectural catch): unlike Qwen3.6 and Qwen3.5 models which bakes MTP heads straight into the base GGUF, Gemma 4 needs a separate draft assistant model downloaded alongside. not a big deal. just don't forget it or MTP won't run. draft assistant GGUF link → comments while you wait for anthropic mythos release, test this and drop your decode numbers below, curious how it scales across different setups.
0:21
analogalok's profile picture

Gemma 4 12B QAT + MTP on 8GB VRAM. llama.cpp flags included. let's run it. 20+ tok/sec decode. 700+ tok/sec prefill. on a single RTX 4060. copy these exact flags: -m gemma-4-12B-it-qat-UD-Q4_K_XL.gguf \ --spec-type draft-mtp \ --spec-draft-n-max 4 \ --spec-draft-p-min 0.7 \ --spec-draft-model gemma-4-12B-it-qat-assistant-MTP-Q8_0.gguf \ -c 48000 -ngl 38 -v → -ngl 99 if you're on 12–24GB VRAM (RTX 3090, 4090, 4080, 3080, 4070 Ti, 3080 Ti) → -ngl 38 for 8GB setups with 48k context (RTX 4060, 3060, 2080, 2070, 3070) → drop it (or the context) lower if you're squeezing on 4–6GB (RTX 2060, 3050, 1660) my rig: RTX 4060 8GB · i7H · 16GB RAM MTP is giving me 25–40% decode throughput gains across Gemma 4 models. nearly zero VRAM cost for that bump. the draft assistant GGUF is only ~300–400MB depending on quant. one thing to know (architectural catch): unlike Qwen3.6 and Qwen3.5 models which bakes MTP heads straight into the base GGUF, Gemma 4 needs a separate draft assistant model downloaded alongside. not a big deal. just don't forget it or MTP won't run. draft assistant GGUF link → comments while you wait for anthropic mythos release, test this and drop your decode numbers below, curious how it scales across different setups.

Alok

28,957 次观看 • 3 个月前

Run Updated Gemma 4 26B A4B QAT (MoE) with Vision at 25 tokens/sec and massive 120k context window on a single RTX 4060 (8 GB VRAM + 16 GB RAM Only!!) Yesterday I pushed Gemma 4 26B A4B QAT to 250k context on a single RTX 4060 using nothing but Q8 KV cache and optimized -b and -ub flags for higher prefill throughput. Today I stacked Multi Token Prediction (MTP) self speculative decoding AND the vision projector (mmproj) on top of that same card, same batch size optimization, same $250 GPU and pushed it until it broke, then found the fix. All text only runs consist of a 28k prompt. vision runs consist of 28k text prompt + an image. # 1. MTP alone. near free decode speed, no catch MTP draft assistant is a separate small model (MTP heads are backed into the main model itself for the qwen 3.5+ models but its a separate small model for gemma 4 series), 240 MB gguf 80k ctx: Prefill 510 t/s | Decode 29.5 t/s 120k ctx: Prefill 433 t/s | Decode 29 t/s 180k ctx: Prefill 240 t/s | Decode 24.9 t/s 250k ctx: Prefill 63 t/s | Decode 13 t/s llama.cpp flags: m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp -md mtp-gemma-4-26B-A4B-it.gguf-c 180000 -b 1024 -ub 1024 --spec-draft-n-max 6 --spec-draft-p-min 0.7 -ctk q8_0 -ctv q8_0 # 2. Add vision on top. the tax you actually pay the vision projector gguf is about 1.1 GBs 80k ctx: Prefill 360 t/s | Decode 25.4 t/s 120k ctx: Prefill 230 t/s | Decode 23.8 t/s 180k ctx (Q8 KV): Prefill 75 t/s | Decode 12.5 t/s - cliff flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp -md mtp-gemma-4-26B-A4B-it.gguf -c 80000 --port 8080 -b 1024 -ub 1024 --spec-draft-n-max 6 --spec-draft-p-min 0.7 -ctk q8_0 -ctv q8_0 --mmproj mmproj-F16.gguf # 3. The fix if you want to run vision over 120k context: swap Q8 KV for Q4 KV past 120k Stack MTP + vision + Q8 KV past 120k context and you hit a wall. draft model overhead plus KV pressure tanks everything. Drop to Q4 KV and the wall disappears: 180k ctx (Q4 KV): Prefill 220 t/s | Decode 25.5 t/s -ctk q4_0 -ctv q4_0 --mmproj mmproj-F16.gguf (rest same as above) Bottom line: MTP gives you a near free +20-30% decode boost up to 120k context. Past that, it's fighting your VRAM, not helping and if vision is loaded too, Q4 KV isn't optional past 120k, it's mandatory. 30% boost is model and card specific, MTP boosted decode 2x for gemma 4 31b on a single rtx 4090. Same 8GB card. Same $250 GPU. Multimodal, speculative decoding, 180k usable context, zero upgrades. You gotta try this if you have a single NVIDIA RTX 3050, 3060, 3070, 4050, 4060, 5050 or 5060. You can try it with a 6 GB VRAM card as well but you will have to lower the context window. Hugging Face links to the updated Unsloth's QAT quants and performance graph are in the replies below. Which models are you running on your 6/8/12GB cards with MTP?
0:20
analogalok's profile picture

Run Updated Gemma 4 26B A4B QAT (MoE) with Vision at 25 tokens/sec and massive 120k context window on a single RTX 4060 (8 GB VRAM + 16 GB RAM Only!!) Yesterday I pushed Gemma 4 26B A4B QAT to 250k context on a single RTX 4060 using nothing but Q8 KV cache and optimized -b and -ub flags for higher prefill throughput. Today I stacked Multi Token Prediction (MTP) self speculative decoding AND the vision projector (mmproj) on top of that same card, same batch size optimization, same $250 GPU and pushed it until it broke, then found the fix. All text only runs consist of a 28k prompt. vision runs consist of 28k text prompt + an image. # 1. MTP alone. near free decode speed, no catch MTP draft assistant is a separate small model (MTP heads are backed into the main model itself for the qwen 3.5+ models but its a separate small model for gemma 4 series), 240 MB gguf 80k ctx: Prefill 510 t/s | Decode 29.5 t/s 120k ctx: Prefill 433 t/s | Decode 29 t/s 180k ctx: Prefill 240 t/s | Decode 24.9 t/s 250k ctx: Prefill 63 t/s | Decode 13 t/s llama.cpp flags: m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp -md mtp-gemma-4-26B-A4B-it.gguf-c 180000 -b 1024 -ub 1024 --spec-draft-n-max 6 --spec-draft-p-min 0.7 -ctk q8_0 -ctv q8_0 # 2. Add vision on top. the tax you actually pay the vision projector gguf is about 1.1 GBs 80k ctx: Prefill 360 t/s | Decode 25.4 t/s 120k ctx: Prefill 230 t/s | Decode 23.8 t/s 180k ctx (Q8 KV): Prefill 75 t/s | Decode 12.5 t/s - cliff flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --spec-type draft-mtp -md mtp-gemma-4-26B-A4B-it.gguf -c 80000 --port 8080 -b 1024 -ub 1024 --spec-draft-n-max 6 --spec-draft-p-min 0.7 -ctk q8_0 -ctv q8_0 --mmproj mmproj-F16.gguf # 3. The fix if you want to run vision over 120k context: swap Q8 KV for Q4 KV past 120k Stack MTP + vision + Q8 KV past 120k context and you hit a wall. draft model overhead plus KV pressure tanks everything. Drop to Q4 KV and the wall disappears: 180k ctx (Q4 KV): Prefill 220 t/s | Decode 25.5 t/s -ctk q4_0 -ctv q4_0 --mmproj mmproj-F16.gguf (rest same as above) Bottom line: MTP gives you a near free +20-30% decode boost up to 120k context. Past that, it's fighting your VRAM, not helping and if vision is loaded too, Q4 KV isn't optional past 120k, it's mandatory. 30% boost is model and card specific, MTP boosted decode 2x for gemma 4 31b on a single rtx 4090. Same 8GB card. Same $250 GPU. Multimodal, speculative decoding, 180k usable context, zero upgrades. You gotta try this if you have a single NVIDIA RTX 3050, 3060, 3070, 4050, 4060, 5050 or 5060. You can try it with a 6 GB VRAM card as well but you will have to lower the context window. Hugging Face links to the updated Unsloth's QAT quants and performance graph are in the replies below. Which models are you running on your 6/8/12GB cards with MTP?

Alok

16,266 次观看 • 1 个月前

没有更多内容可加载