Opus-level intelligence running fully local at home on dual... RTX 4090s. Qwen3.8-27B-GGUF: - 80 tok/s - Full 262k context - MTP on - Only 34 GB of 48 GB VRAM used - Outperforms Claude Opus max on SWE-Pro: 61.7 vs Claude Opus 4.6’s 53.4 GPQA: 89.2 vs 91.3 No need API bills, Or no rate limits. Local frontier-class models are no longer theoretical.show more

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?show more

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?show more

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?show more

167 tok/s on a single RTX 4090. FreeToken just... pushed Qwen3.6-35B-A3B NVFP4 into ridiculous territory. → RTX 4090 24GB → 35B total parameters → ~3B active per token → NVFP4 → 167 tok/s decode → 23.55GB peak VRAM → No speculative decoding → No MTP → No draft model That last part is what makes this interesting. The speed isn’t coming from guessing future tokens. FreeToken is exploiting the MoE architecture directly, keeping the active experts on the GPU while using bandwidth-aware execution for the rest. A 35B model with only ~3B active parameters running at 167 tok/s on a consumer 4090 is exactly why MoE models are becoming so compelling for local AI.show more

HERMES AGENT NOW RUNS CLAUDE OPUS 5. NEAR FABLE... 5 INTELLIGENCE. HALF THE PRICE. SELF-VERIFIES ITS OWN WORK. AVAILABLE TODAY VIA NOUS PORTAL (20% OFF ALL MODELS). Anthropic shipped Opus 5 on July 24, 2026. same $5/$25 per million tokens as Opus 4.8. but the benchmarks tell a different story. WHAT CHANGED FROM OPUS 4.8: FrontierBench v0.1: Opus 5: 43.3%. Opus 4.8: 18.7%. 2.3x jump on the same test. ARC-AGI-3: Opus 5: 30.2%. 3x better than the next closest model. beat Fable 5 on 8 out of 13 benchmarks. at half the cost ($5/$25 vs $10/$50). same price as Opus 4.8. twice the intelligence. no reason to stay on 4.8. THE SPECS: model ID: claude-opus-5 context: 1M tokens (default and maximum) max output: 128K tokens thinking: on by default effort toggle: low / medium / high per request fast mode: $10/$50, 2.5x faster knowledge cutoff: May 2026 minimum cacheable prompt: 512 tokens (was 1,024) SELF-VERIFICATION (the biggest change): Opus 5 checks its own work automatically. Anthropic says: delete your verification prompts. "include a final verification step" now causes OVER-verification because the model already does it. for Hermes /goal tasks this is a direct upgrade. the judge checks evidence. the model also checks evidence. double layer of verification without extra tokens. EFFORT TOGGLE: low: fast, cheap, routine work. medium: balanced, daily tasks. high: full reasoning, complex problems. set per request. not a global switch. matches Hermes /reasoning command: /reasoning low (routine) /reasoning high (complex) Opus 5 effort toggle + Hermes reasoning control = precise cost management per turn. WHERE OPUS 5 FITS IN HERMES: DAILY DRIVER (replaces Opus 4.8): same price. 2.3x better benchmarks. set as your main model: Desktop app / Dashboard: Models → claude-opus-5 CHIEF OF STAFF: synthesis across multiple agents. reads Kanban, prioritizes, routes tasks. self-verification catches routing errors before they cascade. COMPLEX CODING: SOTA on agentic coding benchmarks. FrontierBench 43.3% = best public model for coding. set as coder profile model. /GOAL TASKS: self-verification + completion contracts = the model proves its work AND double-checks the proof. long-horizon goals finish correctly more often. MoA AGGREGATOR: strongest synthesis model at $5/$25. pair with GPT-5.6 and Grok 4.5 as references. Opus 5 aggregates. best quality at mid-range price. presets: max-quality: reference_models: - provider: openai-codex model: gpt-5.6-sol - provider: xai model: grok-4.5 aggregator: provider: anthropic model: claude-opus-5 COMPUTER USE: near-Fable 5 quality for browser automation. at half the token cost per session. computer_use tasks burn lots of vision tokens. Opus 5 halves that bill vs Fable 5. WHAT TO KEEP OPUS 5 AWAY FROM: cron monitoring: too expensive. use DeepSeek or no_agent mode. sub-agent grunt work: use GPT-5.6 Luna ($1/$6) or DeepSeek. auxiliary tasks: use Gemini Flash. routine web extraction: use a cheap model. Opus 5 is for the turns where quality compounds. planning, synthesis, verification, complex reasoning. budget models handle everything else. NOUS PORTAL: 20% OFF ALL MODELS Nous Portal currently runs a 20% discount on all models including Opus 5. $5/$25 official → $4/$20 through Nous Portal. the cheapest way to run Opus 5 right now. hermes setup --portal select claude-opus-5 as your model. discount applies automatically. Opus 5 replaces Opus 4.8 everywhere. same price. better at everything. no tradeoff. straight upgrade. hermes update /model claude-opus-5show more

Qwen3.8-27B有点牛逼， 把接近Opus的能力， 塞进一张消费级显卡，这是掀桌子了？！ 一张24G的卡就能本地跑Claude Opus 4.6了，完全私有🤯！ 相当于把Opus级别的编码能力塞进一张大家都用得起的RTX 5090卡上， 200... tok/s，编码能力直接超过Opus 4.6， 咱们先看数字， SWE-bench Pro 61.7，Claude Opus 4.6 Max 53.4。 OSWorld 84.3，Opus 72.7。 编码和Agent能力，这个27B的开源模型打赢了曾经的闭源巅峰模型， 纯推理还有差距，GPQA和HLE落后，但编码、工具调用、操作电脑，这是大多数人每天用AI干的事。 200 tok/s什么概念？ SGLang加NVFP4加投机解码，单卡5090实测206 tok/s。 比你读字快，比大多数API响应快，而且跑在你自己机器上。 没网络延迟，没token计费，数据不出门。 门槛极低， Q4量化权重17到18GB，一张24GB的卡就够。 二手3090一千多美元，Q4跑40到70 tok/s，写代码完全够用。 4090更快，5090 32GB是消费级天花板，Q6/Q8随便上，长上下文不慌。 M4 Pro 48GB也能跑，安静省电，就是慢点。 跑法很简单， LM Studio或Ollama，等GGUF量化包出来点一下就行。 追求速度上SGLang，Day-0就支持了。 Unsloth已经发了量化版，Hugging Face和ModelScope直接下。show more

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.show more

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 todayshow more

you're paying $20/mo for something your $500 GPU can... already do. Gemma 4 26B A4B QAT MoE + Hermes Agent running on a single RTX 4060 (8GB VRAM). Built a vision capable, 100% free, 100% local, private AI assistant that lives in my Chrome browser. No API keys. No cloud. No subscriptions. 100% vibe coded. 0% handholding. It has full context of whatever's on my screen can answer questions, summarize pages, extract data, and see images. Same local model handles everything, no external calls, ever. keep reading for the model and hermes agent tips i learnt while building this locally. Here's the exact setup for anyone running local LLMs on 6-8 GB VRAM: llama.cpp server flags (on my NVIDIA RTX 4060 8gb VRAM): -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf --cache-type-k q8_0 --cache-type-v q8_0 -c 150000 --port 8080 Throughput with quantization: Prefill: 200-250 tokens/sec Decode: 20-25 tokens/sec reduce context if oom on 6 gb vram card. Key learnings: - Quantize KV cache to q8 for faster prefill/decode. Prefill goes from 100-150 (unquantized) to 200-250 tok/s (q8). - But watch out, once actual context grows past ~50k tokens on high entropy workloads, q8 KV quantization can cause hallucinations. Low entropy workloads are mostly unaffected. If you see it happening, drop the quantization. This is common across all local models. - In Hermes Agent settings -> Memory & Context, bump compression threshold from default 0.5 to 0.7. Default triggers way too frequent context compression and eats time. Up next: add persistent memory, web search, tool calling, streaming output and whatever you suggest. Running a 26B MoE with vision + 150k context window on 8GB VRAM would've sounded impossible 6 months ago. Works the same on the NVIDIA RTX 3060 Ti, 3070, 4060 Ti, 5060, 2080, or any 8GB card. VRAM is the only requirement. Local AI agents are closer than people think. You just need to know where the knobs are. Model's Unsloth quant hugging face link in the comments. Have you tried Hermes agent by Nous Research yet? What are you building with local LLMs? Drop it below, let's see what this community is shipping.show more

SpaceXai just made grok 4.5 FREE in your coding... agent starting today it's xAI's new coding model. 500k context. built for long agent sessions. no card. what you get for $0: -83.3% on terminal-bench 2.1 -64.7% on swe-bench pro - 4.2x more efficient than Opus 4.8 -500k context for big repos -$2/M in, $6/M out once it goes paid what this replaces: -Claude Opus 4.8: $15/M in, $75/M out -SuperGrok: $30-50/mo all for $0 how to set it up (2 min): >curl -fsSL | bash > grok → localhost:8000/v1 > point hermes / aider / opencode / cline to it > model: grok-4.5 Or API key at - base url Works in Hermes, Aider, OpenCode, Cline, Claude Code, and any OpenAI-compatible tool. Important: Free for a limited time. EU waits till mid-July. Rate limits apply. bookmark this before the free window closesshow more

single RTX 3090. 24 GB VRAM. Qwen3.5-35B-A3B. 4-bit quant,... 113 tokens per second at full 262K context harnessing Claude Code locally with no API, no subscription, no proxy. told it what it is. 30 Mamba2 layers, 10 attention, 256 experts, 8 active per token. said "build something that shows off what you can do." it visualized its own architecture. interactive. tokens flowing through layers. 256 experts lighting up on routing. served in the browser from the same GPU running inference. single prompt. then i said level up. 3D. Three.js. separate files. flythrough camera. clickable layers. it planned first, scaffolded 6 files, hit one API bug, fixed it itself, then optimized for smooth framerate. two iterations to a working 3D neural network explorer. llama.cpp just merged a native Anthropic endpoint. Claude Code points at localhost. the whole setup is two commands. no LiteLLM. no proxy config. the open source models coming out of china right now are genuinely changing what's possible on consumer hardware. respect to the Qwen team. this is acceleration.show more

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.show more

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.show more

Qwen3.8-Flash-Next is starting to feel like the local model... Opus fans have been waiting for. Someone ran the NVFP4 176B-class Flash-Next on 2× DGX Sparks, and the results are wild. Real measured scaling → C1: 44.2 tok/s → C2: 64.6 tok/s → C4: 86.8 tok/s aggregate The per-stream speed drops with concurrency, but total throughput keeps climbing. Long-context behavior was even more impressive: → 5K: needle retrieved → 21K: needle retrieved → 84K: needle retrieved → 167K: needle retrieved → 262K: prefill succeeded, but the window was saturated That 167K retrieval test is the one I care about. Long agent runs are where models usually start losing the plot. Flash-Next didn’t. It also held up surprisingly well on physics-heavy reasoning, artifact generation, research workflows, evidence checking, and long-horizon planning. The personality is interesting too. DeepSeek V4 Flash feels like the dependable workhorse. GLM-5.2 feels like the problem-solving machine. Qwen3.8-Flash-Next feels more insightful. It has that rare ability to understand what you’re actually asking rather than just following the surface pattern. The main weakness I’ve noticed is instruction following. It can occasionally drift between prose turns where DeepSeek and GLM stay tighter. And this is why the 256GB M5 Ultra conversation gets interesting. If Apple can pair that huge unified-memory pool with enough bandwidth, this model class becomes genuinely practical for long-running local agents. We’re talking about frontier-class reasoning on hardware sitting on a desk.show more

Which local models can actually handle tool calling? I... built a framework to find out. 15 scenarios. 12 tools. Mocked responses. Temperature 0. No cherry-picking. Tested every Qwen3.5 size from 0.8B to 397B, and since some of you asked after the distillation tests: yes, I included Jackrong's Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled too. Only two models went all green: the 27B dense and the distilled 27B. The 397B? Failed two tests. The 122B? Failed one. The 35B? Failed two. The timed-out results — mostly on the smaller models, are cases where the model got stuck in a loop, repeating the same tool call until it hit the 30-second limit. The test that exposed the most models: "Search for Iceland's population, then calculate 2% of it." Simple, but 35B, 122B, and 397B all used a rounded number from memory instead of the actual search result. They didn't trust their own tool output. Small models hallucinate data. Big models ignore data. The 27B just threaded it through.show more

a moonshot engineer leaked the benchmark anthropic, openai and... xai all buried the same week: kimi k3 beat opus 5, gpt-5.6 and grok 4.6 at $0.94 a task. stop paying anthropic $200 a month for opus 5 and openai $200 for gpt-5.6 when kimi does the same work for $8 the leak showed kimi k3 winning 9 of 12 categories against opus 5, gpt-5.6 and grok 4.6. within 48 hours all three labs quietly pushed pricing pages and one very specific comparison chart off their sites. nobody announced anything. they just deleted, which tells you everything the four numbers they scrubbed: cost per task · $0.94 vs $1.80 -> opus 5 charges $1.80 to finish one task. gpt-5.6 $1.04. grok 4.6 $0.61. kimi k3 $0.94 and it landed 487 of 500 clean -> anthropic is billing you double for a model that lost the benchmark it paid to promote the weights · free, sitting on huggingface right now -> the entire model is a public download. pull it, keep it, run it forever, nobody can switch it off -> a model you can hold cannot be rented at $200 a month. that single fact is what three labs deleted a chart over the switch · one line of bash -> moonshot ships an anthropic-compatible endpoint. one env variable and claude code points at kimi -> same cli, same keybindings, same /model. you change a url, opus 5 never knows it lost the seat the bill · $400 down to $8 -> opus 5 max plus gpt-5.6 pro is $400 a month. kimi runs the same daily work for $8 metered -> that is a 98% cut for output that beat both of them 9 categories to 3 here is the part they will fight me on: the frontier tax died the week this leaked and all three labs know it. once the weights are public the price has a ceiling, because anyone can serve the same model. anthropic, openai and xai are charging 2025 prices on a lead that ended in a benchmark they deleted instead of answered drop your $400/mo ai stack to $8. the run above is kimi k3 finishing the task opus 5 bills $1.80 for. the full breakdown is in the article belowshow more

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.show more

look what a single consumer GPU just built. gave... Qwen3.5-35B-A3B one prompt: build a cloud GPU marketplace with pricing cards, deploy templates, and a benchmark leaderboard. it planned the layout, wrote the animations, populated the data, and served it. one shot. one HTML file. then i told it to iterate. split the hero, add a floating GPU with neural network animation. glassmorphism on the cards. done. done. done. three rounds, no confusion, no regressions. 4-bit quantized. 19.7 GB. single RTX 3090. full coding agent claude code harness running on localhost. no API calls leaving my machine. no subscription. no rate limits. earlier today i pointed it at my own production website. it curled the HTML, found every broken link, and told me "pretty shell, empty core. would not recommend." then built a better version from scratch. local inference stops being a demo when you actually steer it. the models are there. they understand intent. but you have to meet them halfway with good prompts, clear context, and real project structure. that's the skill gap now. not the models. the steering. more experiments coming. i genuinely cannot stop playing with this thing.show more

We are in an insane run of open-weight drops.... Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B MoE refresh, Terminal-Bench 2.1 jumps 61.8→82.7 over the preview, DeepSWE 7.3→54.4. Closes in on Opus-4.8 on Agents' Last Exam (25.2 vs 25.7). MIT. → Muse-Glimmer-30B, from Meta (they are back!!): their first open agentic model. ~29.6B dense + perception encoder, 131k+ context, built to run fully local, no cloud. Apache 2.0. → Liquid AI LFM2.5-2.6B: 2.69B params, 131k context, 220 tok/s on an M5 Max in under 2.5GB RAM. Competitive with models 4x larger on agentic tasks. → inclusionAI Ling-3.0-flash: 124B total, only 5.1B active, ~12% the size of their old 1T flagship Ring-2.6, matches it on key benchmarks. MIT. → inclusionAI Ling-3.0-tiny: 7.9B total, 1.3B active, 86-90 tok/s on an M4 Pro MacBook at ~8GB peak memory. MIT. → NVIDIA Nemotron-3.5-Lightning-30B-A3B: hybrid Mamba-2+MoE+Attention, up to 1M context, runs on a single H100 or DGX Spark, SWE-bench Verified 52.8. → deepgrove maple-preview: 20B-A1B ternary-weight reasoner, 218 tok/s on a Mac mini M4, 5.3GB checkpoint. MIT. → BigBang-v1 (endless-frontier): fine-tuned from Qwen3.6-35B-A3B via a self-evolving generator/critic synthetic-data loop. Lands aggregate performance between DeepSeek V4 Flash (284B) and V4 Pro (1.6T), at 35B. Apache 2.0. 🎬 Video → MiniMax-H3: 33B dense omni model, native stereo audio, up to 2K/15s. 3.6k+ likes already. → Minimax-H3-Turbo (lightx2v): Apache-2.0 turbo distillation of H3 for fast inference. → Lightricks LTX-2.5: image-to-video update, custom Gemma-4-12B text encoder, a markedly stronger distilled model. 🔊 Voice → NVIDIA NemotronLabs VoiceChat-11B: full-duplex speech-to-speech, ~450ms turn-taking, #2 on open VoiceBench, and the first open full-duplex model with live tool-calling mid-conversation. 🛡️ Safety → Mistral Shieldstral-1.0-3B: 3B multimodal guardrail that takes your safety policy as plain text instead of fixed categories. Beats LlamaGuard-4-12B and ShieldGemma-9B on HarmBench (99.4) and ToxicChat (84.1) at a fraction of the size. Apache 2.0.show more

Claude + Obsidian + n8n + 316 TB storage... built a private second brain that ships AI projects at $3,400 a month. Most people rent cloud space and pray the bills stay low. Data leaks. Models throttle. Projects slow. This stack runs everything local. → Obsidian vault grows without limits. Every note, dataset, fine-tune, client archive links in one graph. → Claude reads the full vault instantly through Projects and MCP. No token caps. No privacy risk. → n8n automates the pipelines. New data drops → auto-ingest → Claude summarizes and links. Nightly fine-tune jobs fire. Client deliverables generate on demand. → One ORICO enclosure starts at 60 TB. Add drives. 180 TB. 300 TB. Final setup hits 316 TB. HDDs for archives. SSDs for active models. Laptop-level speed in a desktop box. Plug, power, done. Month 1: Vault hits 120 GB. First local agent runs end-to-end. Month 2: Private dataset training. Sold one custom workflow for $1,200. No cloud fees. Month 3: Recurring retainers. $3,400. System trains, tests, and deploys while you review. Before: Scattered cloud tabs. Monthly bills. Slow inference. After: 316 TB under your desk. Full control. Zero latency. Projects compound. The second brain does not beg for API keys. It owns the data and prints the income. If this was useful - follow.show more