Loading video...

Video Failed to Load

Go Home

A $351 MINI PC IS RUNNING 26-BILLION-PARAMETER AI MODELS AT 20 TOKENS/SEC AND HERMES AGENT ON TOP OF IT This is the Minisforum UM790 Pro. AMD Ryzen 9 7940HS, Radeon 780M iGPU, 48GB DDR5. The BIOS reports the GPU has 4GB of VRAM Here's the part people get wrong....

slash1sol's profile picture

slash1s

8,689 subscribers

35,742 views • 3 months ago •via X (Twitter)

GamingEducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

HERMES AGENT NOW RUNS ON AN 8GB LAPTOP GPU JUST AS EASILY AS IT RUNS ON A 128GB MINI PC Nous Research shipped the official Hermes Agent Desktop App this week. Someone pointed it at a local llama server running on an RTX 4060 with 16GB system RAM. The integration took two minutes The model behind it: Gemma 4 26B MoE, QAT quantized, running on 8GB of VRAM. A 60k token prompt held a stable 20 tokens a second, flat, no slowdown as context grew. The flags were nothing exotic, just -cmoe -c 248000 on llama.cpp What that 8GB setup does out of the box: reads and patches its own code, runs it in a terminal, debugs errors, manages GitHub repos, spawns sub-agents for parallel work. Browses the web with vision to debug a UI. Schedules cron jobs in plain language. Connects to Notion, Google Workspace, Linear, and Obsidian to manage tasks on its own That's the same agent layer running on a Minisforum MS-S1 MAX with 128GB of unified memory, 96GB of it to the GPU, holding a 120B model at 56 tokens a second instead of a 26B model at 20. Same software, same tool execution, same zero API key. The only thing that changes between an $800 laptop and a $2,000 mini PC is how big a model you can afford to run underneath it The barrier to running a real autonomous agent locally didn't just drop. It dropped all the way down to hardware most people already own
0:20

HERMES AGENT NOW RUNS ON AN 8GB LAPTOP GPU JUST AS EASILY AS IT RUNS ON A 128GB MINI PC Nous Research shipped the official Hermes Agent Desktop App this week. Someone pointed it at a local llama server running on an RTX 4060 with 16GB system RAM. The integration took two minutes The model behind it: Gemma 4 26B MoE, QAT quantized, running on 8GB of VRAM. A 60k token prompt held a stable 20 tokens a second, flat, no slowdown as context grew. The flags were nothing exotic, just -cmoe -c 248000 on llama.cpp What that 8GB setup does out of the box: reads and patches its own code, runs it in a terminal, debugs errors, manages GitHub repos, spawns sub-agents for parallel work. Browses the web with vision to debug a UI. Schedules cron jobs in plain language. Connects to Notion, Google Workspace, Linear, and Obsidian to manage tasks on its own That's the same agent layer running on a Minisforum MS-S1 MAX with 128GB of unified memory, 96GB of it to the GPU, holding a 120B model at 56 tokens a second instead of a 26B model at 20. Same software, same tool execution, same zero API key. The only thing that changes between an $800 laptop and a $2,000 mini PC is how big a model you can afford to run underneath it The barrier to running a real autonomous agent locally didn't just drop. It dropped all the way down to hardware most people already own

NO1ennn

40,079 views • 3 months ago

i pointed hermes agent at nvidia's nemotron cascade 2 30B-A3B on a single RTX 3090 24GB. IQ4_XS quant by bartowski, 187 tok/s, 625K context. had it discover its own hardware, create an identity file, then build a full GPU marketplace UI from a single prompt. it one shotted it. first attempt no iteration. qwen 3.5 35B-A3B on the same hardware same 3090 24GB took an iteration to recover from a blank screen on the same type of build. 24 days between these two models releasing. same active parameters, completely different architectures and cascade 2 through hermes agent just keeps going. this model goes on and on. feast your eyes. more iterations and tests dropping soon. nvidia really cooked. no special flags needed. nvidia optimized this mamba MoE so well it just runs. flash attention auto enabled, context auto allocated. the model does the work not the config. but i compiled llama.cpp from source and i'm not sure how it performs on other engines. if you ran nemotron on any hardware drop your numbers below. RTX, AMD, Mac, whatever. model, quant, tok/s, engine. i want to see if it holds everywhere or just on llama.cpp.
1:31

i pointed hermes agent at nvidia's nemotron cascade 2 30B-A3B on a single RTX 3090 24GB. IQ4_XS quant by bartowski, 187 tok/s, 625K context. had it discover its own hardware, create an identity file, then build a full GPU marketplace UI from a single prompt. it one shotted it. first attempt no iteration. qwen 3.5 35B-A3B on the same hardware same 3090 24GB took an iteration to recover from a blank screen on the same type of build. 24 days between these two models releasing. same active parameters, completely different architectures and cascade 2 through hermes agent just keeps going. this model goes on and on. feast your eyes. more iterations and tests dropping soon. nvidia really cooked. no special flags needed. nvidia optimized this mamba MoE so well it just runs. flash attention auto enabled, context auto allocated. the model does the work not the config. but i compiled llama.cpp from source and i'm not sure how it performs on other engines. if you ran nemotron on any hardware drop your numbers below. RTX, AMD, Mac, whatever. model, quant, tok/s, engine. i want to see if it holds everywhere or just on llama.cpp.

Sudo su

71,535 views • 6 months ago

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

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

264,581 views • 4 months ago

this is what 12gb of vram builds in 2026, absolute magic > rtx 3060 12gb, #1 gpu on steam > bonsai 2 27b + mtp, 5.95 gb of weights > hermes agent, 5 hours, 328k tokens written > 8 js files, 2,368 lines, zero hand written code > 50 tok/s fresh, 22 tok/s average, 125k context watch the full video, 5 hours in 12 minutes of pure dance of a local ai model on rtx 3060 12gb vram, and stay till the end for the full gameplay. this entire game was built by bonsai2, a qwen 3.8 27b dense compressed to ternary, and this small model is punching way above its weight. it built multi file engineering work using hermes agent, sure it's not fast but perfect for overnights and routine work and the quality is insane, and context holding is another best one, it does not lose the thread. i ran PrismML bonsai 1 made from qwen 3.6 27b dense and i built things with it, but this time with the latest base model qwen 3.8 these results are insane, and because i loved building with it a lot i thought many more of you would run it because this gpu exists in almost every home. so i packaged mtp, doubled the speed from 26 tok/s to 50 tok/s, packed the prefill fix in and released it on huggingface, almost 4,000 downloads in 3 days. i'll leave a link below.
15:03

this is what 12gb of vram builds in 2026, absolute magic > rtx 3060 12gb, #1 gpu on steam > bonsai 2 27b + mtp, 5.95 gb of weights > hermes agent, 5 hours, 328k tokens written > 8 js files, 2,368 lines, zero hand written code > 50 tok/s fresh, 22 tok/s average, 125k context watch the full video, 5 hours in 12 minutes of pure dance of a local ai model on rtx 3060 12gb vram, and stay till the end for the full gameplay. this entire game was built by bonsai2, a qwen 3.8 27b dense compressed to ternary, and this small model is punching way above its weight. it built multi file engineering work using hermes agent, sure it's not fast but perfect for overnights and routine work and the quality is insane, and context holding is another best one, it does not lose the thread. i ran PrismML bonsai 1 made from qwen 3.6 27b dense and i built things with it, but this time with the latest base model qwen 3.8 these results are insane, and because i loved building with it a lot i thought many more of you would run it because this gpu exists in almost every home. so i packaged mtp, doubled the speed from 26 tok/s to 50 tok/s, packed the prefill fix in and released it on huggingface, almost 4,000 downloads in 3 days. i'll leave a link below.

Sudo su

87,876 views • 13 days ago

125B on a single RTX 4090 at 25 tok/s is actually insane Qwen3.8-Flash-Next + MTP is hitting: 80K context 25.35 tok/s decode 471 tok/s prefill On one consumer GPU. Yes, it’s an MoE, so you’re not running all 125B parameters for every token. But still, getting a model this large to run this fast on a 4090 is wild. MTP is doing a lot of the heavy lifting here too. Instead of generating one token at a time, it can speculate on multiple tokens and verify them together. And 25 tok/s is the important number.
0:20

125B on a single RTX 4090 at 25 tok/s is actually insane Qwen3.8-Flash-Next + MTP is hitting: 80K context 25.35 tok/s decode 471 tok/s prefill On one consumer GPU. Yes, it’s an MoE, so you’re not running all 125B parameters for every token. But still, getting a model this large to run this fast on a 4090 is wild. MTP is doing a lot of the heavy lifting here too. Instead of generating one token at a time, it can speculate on multiple tokens and verify them together. And 25 tok/s is the important number.

FHILY👑

39,979 views • 1 month ago

nemotron 3 omni q8 on dgx spark 128gb vram cranking via hermes agent at 56 tok/s. first night of real local agentic on this box and local hits harder than i thought it would. q8 (near lossless quant, perplexity loss <1% vs fp16) running 256k context on 33 gb of unified memory, 90+ gb still free. multimodal omni weights included. hermes agent driving from telegram, talking to it from bed. speed: 56 tok/s generation, 1,300 tok/s prefill. for context, qwen 3.6 27b at q4 (heavy quant) on 3090 = 40 tok/s. nemotron at higher precision quant on spark beats qwen at lower precision quant on 3090. moe 3.5b active params architecture earns its keep. what i tested tonight: agentic tool calling works clean. ask it to check disks, it autonomously runs df -h through hermes agent. ask it to set up telegram gateway, it invokes the hermes-agent skill, walks through the prompts, completes the flow. overthinks a bit before tool calls (reasoning model trait) but lands the right move every time. researches api docs, internalizes, tests, documents. completes tasks. current models on dgx spark: 9 gguf files, 305 gb total, mix of qwen 3.6 27b dense (5 quants), nemotron omni (4 quants), deepseek v4-flash 158b q4 (the 112gb flagship test). more data coming this week as i benchmark each.
1:40

nemotron 3 omni q8 on dgx spark 128gb vram cranking via hermes agent at 56 tok/s. first night of real local agentic on this box and local hits harder than i thought it would. q8 (near lossless quant, perplexity loss <1% vs fp16) running 256k context on 33 gb of unified memory, 90+ gb still free. multimodal omni weights included. hermes agent driving from telegram, talking to it from bed. speed: 56 tok/s generation, 1,300 tok/s prefill. for context, qwen 3.6 27b at q4 (heavy quant) on 3090 = 40 tok/s. nemotron at higher precision quant on spark beats qwen at lower precision quant on 3090. moe 3.5b active params architecture earns its keep. what i tested tonight: agentic tool calling works clean. ask it to check disks, it autonomously runs df -h through hermes agent. ask it to set up telegram gateway, it invokes the hermes-agent skill, walks through the prompts, completes the flow. overthinks a bit before tool calls (reasoning model trait) but lands the right move every time. researches api docs, internalizes, tests, documents. completes tasks. current models on dgx spark: 9 gguf files, 305 gb total, mix of qwen 3.6 27b dense (5 quants), nemotron omni (4 quants), deepseek v4-flash 158b q4 (the 112gb flagship test). more data coming this week as i benchmark each.

Sudo su

30,228 views • 5 months ago

i spent 3 hours finding the sweet spot for hermes 4.3 36B on a single RTX 3090. saving you the trouble, anon. the model is 21.8GB at Q4_K_M. that leaves 2.2GB free on 24GB VRAM. not much room for KV cache. here's what actually happened: 4K: 35.3 tok/s 8K: 35.2 tok/s 16K: 34.8 tok/s 32K: 34.6 tok/s 64K: 6.4 tok/s 128K: 1.9 tok/s flat from 4K to 32K. then it falls off a cliff at 64K. the trick is quantized KV cache. without it you OOM at 16K. with quantized KV cache you get 32K at full speed. all 64 layers on GPU. at 64K something weird happens. ngl 99 (all layers on GPU) = 3.96 tok/s. the KV cache silently spills to CPU. drop to ngl 55 and speed jumps to 6.37. drop to ngl 48 and it gets worse again (3.46). there's an offload sweet spot where you free just enough VRAM for the cache without losing too much compute to PCIe transfers. 128K works at ngl 32 but you're at 1.95 tok/s. half the model on CPU. usable for batch work, not for interactive. the sweet spot command: llama-server -m hermes-4.3-36b-Q4_K_M.gguf -ngl 99 -c 32768 --cache-type-k q4_0 --cache-type-v q4_0 32K context. 34.6 tok/s. all on GPU. this is where dense 36B lives on 24GB. for comparison, qwen 3.5 (35B MoE, 3B active) holds 112 tok/s from 4K all the way to 262K on the same GPU. no speed drop. same total params, completely different architecture. hybrid linear attention means flat context scaling. dense pays for every token in the KV cache. code and quality comparison coming next. fast vs slow generation side by side in the videos below.
2:29

i spent 3 hours finding the sweet spot for hermes 4.3 36B on a single RTX 3090. saving you the trouble, anon. the model is 21.8GB at Q4_K_M. that leaves 2.2GB free on 24GB VRAM. not much room for KV cache. here's what actually happened: 4K: 35.3 tok/s 8K: 35.2 tok/s 16K: 34.8 tok/s 32K: 34.6 tok/s 64K: 6.4 tok/s 128K: 1.9 tok/s flat from 4K to 32K. then it falls off a cliff at 64K. the trick is quantized KV cache. without it you OOM at 16K. with quantized KV cache you get 32K at full speed. all 64 layers on GPU. at 64K something weird happens. ngl 99 (all layers on GPU) = 3.96 tok/s. the KV cache silently spills to CPU. drop to ngl 55 and speed jumps to 6.37. drop to ngl 48 and it gets worse again (3.46). there's an offload sweet spot where you free just enough VRAM for the cache without losing too much compute to PCIe transfers. 128K works at ngl 32 but you're at 1.95 tok/s. half the model on CPU. usable for batch work, not for interactive. the sweet spot command: llama-server -m hermes-4.3-36b-Q4_K_M.gguf -ngl 99 -c 32768 --cache-type-k q4_0 --cache-type-v q4_0 32K context. 34.6 tok/s. all on GPU. this is where dense 36B lives on 24GB. for comparison, qwen 3.5 (35B MoE, 3B active) holds 112 tok/s from 4K all the way to 262K on the same GPU. no speed drop. same total params, completely different architecture. hybrid linear attention means flat context scaling. dense pays for every token in the KV cache. code and quality comparison coming next. fast vs slow generation side by side in the videos below.

Sudo su

52,268 views • 7 months ago

a regular laptop with just 8GB VRAM can now run a LOCAL AI AGENT directly on your device what you need: 1/ 8 GB VRAM 2/ 16 GB RAM 3/ $600+ laptop method: Kimi K2 + Hermes Agent Dekstop App what agent can do: 1/ read and write files 2/ patch code, open PRs on GitHub 3/ browse the web like a human 4/ work with Notion 5/ run scripts, debug, refactor this isn't 'ask a question, get an answer.' this is an agent that drives a task from start to finish on its own. before: local agent = either the cloud and $$$, or an RTX now: any gaming laptop from the last 3 years p.s. MoE is the key. Kimi K2 activates only a fraction of its params per token - that's why a 1T-param model runs on hardware where a dense 26B would already be choking did you try Hermes Dekstop?
0:20

a regular laptop with just 8GB VRAM can now run a LOCAL AI AGENT directly on your device what you need: 1/ 8 GB VRAM 2/ 16 GB RAM 3/ $600+ laptop method: Kimi K2 + Hermes Agent Dekstop App what agent can do: 1/ read and write files 2/ patch code, open PRs on GitHub 3/ browse the web like a human 4/ work with Notion 5/ run scripts, debug, refactor this isn't 'ask a question, get an answer.' this is an agent that drives a task from start to finish on its own. before: local agent = either the cloud and $$$, or an RTX now: any gaming laptop from the last 3 years p.s. MoE is the key. Kimi K2 activates only a fraction of its params per token - that's why a 1T-param model runs on hardware where a dense 26B would already be choking did you try Hermes Dekstop?

kaize

58,760 views • 4 months ago

Anyone with 8GB or 12GB VRAM setups needs to understand that "-ncmoe" is the key flag to boost performance on llama.cpp Here are my results for Qwen3.6 35B A3B, with 64k q8_0 context on a 8GB RTX 3070Ti: ⚪️ no flag → 8.7 tok/s RAM: 13.6GB & VRAM: 7.8GB 🔴 -ncmoe 35 → 27.5 tok/s RAM: 12.1GB & VRAM: 4.3GB 🟢 -ncmoe 30 → 32.5 tok/s RAM: 12GB & VRAM: 5.6GB 🔵 -ncmoe 25 → 40.9 tok/s RAM: 12GB & VRAM: 6.9GB Please note the ram and vram usage you see are total usage of a windows pc, with the model running. My friend's setup: 8GB VRAM and 16GB RAM. You can boost performance by switching to Linux, just something to keep in mind. Basically, this flag keeps the MoE experts in the first X layers on your CPU + RAM, instead of eating all your VRAM straight away. This is a smart hybrid offload way that lets you run bigger models without OOM while keeping the rest on your GPU for speed. As we can see on the data, there's a sweet spot. When we lower it from 35 to 25, speed bumps +50% because there are more layers on your GPU (look at the VRAM usage). The key here is to play around with the number and fit as much as possible on your VRAM, goal is to have 1GB/800MB headroom to avoid stress. ↓ server flags below
0:37

Anyone with 8GB or 12GB VRAM setups needs to understand that "-ncmoe" is the key flag to boost performance on llama.cpp Here are my results for Qwen3.6 35B A3B, with 64k q8_0 context on a 8GB RTX 3070Ti: ⚪️ no flag → 8.7 tok/s RAM: 13.6GB & VRAM: 7.8GB 🔴 -ncmoe 35 → 27.5 tok/s RAM: 12.1GB & VRAM: 4.3GB 🟢 -ncmoe 30 → 32.5 tok/s RAM: 12GB & VRAM: 5.6GB 🔵 -ncmoe 25 → 40.9 tok/s RAM: 12GB & VRAM: 6.9GB Please note the ram and vram usage you see are total usage of a windows pc, with the model running. My friend's setup: 8GB VRAM and 16GB RAM. You can boost performance by switching to Linux, just something to keep in mind. Basically, this flag keeps the MoE experts in the first X layers on your CPU + RAM, instead of eating all your VRAM straight away. This is a smart hybrid offload way that lets you run bigger models without OOM while keeping the rest on your GPU for speed. As we can see on the data, there's a sweet spot. When we lower it from 35 to 25, speed bumps +50% because there are more layers on your GPU (look at the VRAM usage). The key here is to play around with the number and fit as much as possible on your VRAM, goal is to have 1GB/800MB headroom to avoid stress. ↓ server flags below

left curve dev

166,478 views • 5 months ago

no prompt engineering, no agentic harness, no tool calls. just me being lazy in llama.cpp's web ui and gemma 4 31b dense taking the task seriously. i typed "create gpu marketplace cards with hardware specs and prices per hour" and the model went and coded this ui, one shot, navy bg, glassmorphism cards, neon accent buttons, realistic pricing tiers per architecture. it even wrote a "why this looks premium" explanation under the code. for context this is a q4 quant of google's 31b dense thinking model, running on a rtx 5090 mobile 24gb in the rog scar 18 at around 15 tok/s sustained, same vram tier as a 3090 or 4090 desktop, so whatever you see here translates directly to your card at home. the whole interaction was me not trying and the model reasoning harder than the prompt deserved. that tells me more about where local ai is at in april 2026 than any leaderboard score. next test drops gemma 4 into hermes agent, autonomous tool calling, multi step reasoning, real agentic loop instead of a chat window. let's see what the same model does when it gets the right environment. more experiments coming anon. octopus invaders queued. same hardware, different tasks, all published here on x and all translatable to your 24gb card. for now the video below shows it coding live, gpu going brrr.
2:23

no prompt engineering, no agentic harness, no tool calls. just me being lazy in llama.cpp's web ui and gemma 4 31b dense taking the task seriously. i typed "create gpu marketplace cards with hardware specs and prices per hour" and the model went and coded this ui, one shot, navy bg, glassmorphism cards, neon accent buttons, realistic pricing tiers per architecture. it even wrote a "why this looks premium" explanation under the code. for context this is a q4 quant of google's 31b dense thinking model, running on a rtx 5090 mobile 24gb in the rog scar 18 at around 15 tok/s sustained, same vram tier as a 3090 or 4090 desktop, so whatever you see here translates directly to your card at home. the whole interaction was me not trying and the model reasoning harder than the prompt deserved. that tells me more about where local ai is at in april 2026 than any leaderboard score. next test drops gemma 4 into hermes agent, autonomous tool calling, multi step reasoning, real agentic loop instead of a chat window. let's see what the same model does when it gets the right environment. more experiments coming anon. octopus invaders queued. same hardware, different tasks, all published here on x and all translatable to your 24gb card. for now the video below shows it coding live, gpu going brrr.

Sudo su

28,939 views • 5 months ago

the tiebreaker is done. qwen 3.5 27B dense. single RTX 3090. one prompt. zero steering. zero human edits. 1,827 lines across 10 files. 13 minutes. full thinking mode. runs on first load. hermes 4.3 got the same prompt with 2x 3090s and 5x the context it needed. wrote 1,249 lines, left empty files, needed 3 interventions, game was broken on load. same architecture class. same quant. hermes got double the hardware. completely different result. dense wasn't the problem. hermes was. but here's what got me. this model thinks at 27 tok/s. every single token carries 27 billion parameters of reasoning. MoE hit 112 tok/s but only 3B active per token. the dense model is slower and it doesn't matter. watch 13 minutes of autonomous coding on a consumer GPU with zero intervention and tell me speed is what matters. a year ago this wasn't possible. now it runs on hardware you can buy used for $900. no API. no subscription. no cloud. just a 3090 doing what data centers did 18 months ago. full unedited session in the video. every token, every file, every thinking chain. 16 minutes. hit play.
16:04

the tiebreaker is done. qwen 3.5 27B dense. single RTX 3090. one prompt. zero steering. zero human edits. 1,827 lines across 10 files. 13 minutes. full thinking mode. runs on first load. hermes 4.3 got the same prompt with 2x 3090s and 5x the context it needed. wrote 1,249 lines, left empty files, needed 3 interventions, game was broken on load. same architecture class. same quant. hermes got double the hardware. completely different result. dense wasn't the problem. hermes was. but here's what got me. this model thinks at 27 tok/s. every single token carries 27 billion parameters of reasoning. MoE hit 112 tok/s but only 3B active per token. the dense model is slower and it doesn't matter. watch 13 minutes of autonomous coding on a consumer GPU with zero intervention and tell me speed is what matters. a year ago this wasn't possible. now it runs on hardware you can buy used for $900. no API. no subscription. no cloud. just a 3090 doing what data centers did 18 months ago. full unedited session in the video. every token, every file, every thinking chain. 16 minutes. hit play.

Sudo su

91,135 views • 7 months ago

running a 405-billion-parameter model used to mean a $30,000 GPU rack. one developer made it run on a single 8GB card the kind that's been sitting in gaming laptops for years. it's called AirLLM, and the trick is almost stupidly simple: instead of loading the whole model, it keeps one layer on the GPU at a time and streams the rest through. / Llama 3.1 405B on 8GB / DeepSeek-V3, all 671B of it, on about 12GB / no quantization, no distillation, no pruning the full-precision model / works with Llama, Qwen, DeepSeek, Mistral, Gemma, and more it's Apache 2.0 and already past 22,600 stars. → bookmark it.
0:21

running a 405-billion-parameter model used to mean a $30,000 GPU rack. one developer made it run on a single 8GB card the kind that's been sitting in gaming laptops for years. it's called AirLLM, and the trick is almost stupidly simple: instead of loading the whole model, it keeps one layer on the GPU at a time and streams the rest through. / Llama 3.1 405B on 8GB / DeepSeek-V3, all 671B of it, on about 12GB / no quantization, no distillation, no pruning the full-precision model / works with Llama, Qwen, DeepSeek, Mistral, Gemma, and more it's Apache 2.0 and already past 22,600 stars. → bookmark it.

dunik

151,882 views • 2 months ago

NVIDIA'S $30K H100 JUST GOT OUT-INFERENCED BY A $250 RYZEN. 18 TOKENS/SEC ON A 35B MODEL, $0.03 IN ELECTRICITY, $47B GONE FROM NVDA BY FRIDAY download qwen3 35b-a3b -> load in lm studio -> disable gpu entirely -> run on cpu + ram -> hit 18 tokens/sec on a 6-core ryzen -> pay nothing per token. that loop is why moe models just made every consumer cpu a viable ai host and nvidia's inference monopoly is quietly on borrowed time. qwen3 35b-a3b + lm studio + ryzen 5 9600x + 32gb ddr5 + zero gpu - that's the stack. watch and save it, then run a 35b model on your laptop this weekend.
6:33

NVIDIA'S $30K H100 JUST GOT OUT-INFERENCED BY A $250 RYZEN. 18 TOKENS/SEC ON A 35B MODEL, $0.03 IN ELECTRICITY, $47B GONE FROM NVDA BY FRIDAY download qwen3 35b-a3b -> load in lm studio -> disable gpu entirely -> run on cpu + ram -> hit 18 tokens/sec on a 6-core ryzen -> pay nothing per token. that loop is why moe models just made every consumer cpu a viable ai host and nvidia's inference monopoly is quietly on borrowed time. qwen3 35b-a3b + lm studio + ryzen 5 9600x + 32gb ddr5 + zero gpu - that's the stack. watch and save it, then run a 35b model on your laptop this weekend.

Antid

23,745 views • 2 months ago

i'm running a 397 billion parameter model on a amd ai max box that sits on my desk and pulls less power than a gaming laptop. the model is Nex-N2-Pro, 397B-A17B, the open weight release people are putting next to gpt-5.5 on coding. i have it quantized to IQ1_M, 1.75 bits per weight, 90gb of weights loaded into the 128gb of unified memory on amd's strix halo igpu. watch the gpu in this recording. it spikes, it sustains, it does not fall over. that is the part the spec sheets never show you, not just that a 400b model loads, but that an integrated graphics chip holds the load and generates token after token, stable, no crash, no thermal cliff. and it is not a slideshow. roughly 18 tokens a second, faster than you can read. a frontier scale model producing usable output, fully local. no datacenter, no rented h100s, no api key, no permission. three years ago a model this size meant a server room and a budget to match. tonight it is a quiet box on my desk. this is the accessible tier almost nobody benchmarks honestly, and it is further along than the timeline thinks. the full breakdown is coming, rocm vs vulkan on this chip, and this little amd box head to head against the nvidia equivalent. stay tuned.
2:18

i'm running a 397 billion parameter model on a amd ai max box that sits on my desk and pulls less power than a gaming laptop. the model is Nex-N2-Pro, 397B-A17B, the open weight release people are putting next to gpt-5.5 on coding. i have it quantized to IQ1_M, 1.75 bits per weight, 90gb of weights loaded into the 128gb of unified memory on amd's strix halo igpu. watch the gpu in this recording. it spikes, it sustains, it does not fall over. that is the part the spec sheets never show you, not just that a 400b model loads, but that an integrated graphics chip holds the load and generates token after token, stable, no crash, no thermal cliff. and it is not a slideshow. roughly 18 tokens a second, faster than you can read. a frontier scale model producing usable output, fully local. no datacenter, no rented h100s, no api key, no permission. three years ago a model this size meant a server room and a budget to match. tonight it is a quiet box on my desk. this is the accessible tier almost nobody benchmarks honestly, and it is further along than the timeline thinks. the full breakdown is coming, rocm vs vulkan on this chip, and this little amd box head to head against the nvidia equivalent. stay tuned.

Sudo su

32,163 views • 3 months ago

small local model that falls apart in bloated agents like openclaw just runs like a wild horse in hermes agent. and that's not even my line, someone else called it that, i've just been quietly pointing people at this harness for months because it held up on everything i threw at it, 3b models all the way to one trillion params. watch this happen on my own machine. i pointed hermes agent at a local http endpoint, gemma 4 12b on my 3090 llama.cpp server, and it auto-detected the model and started working immediately. no config wrestling, no broken tool calls, no babysitting the output format, i typed in a url and it just went. the whole clip is exactly that, start to finish, no errors, no retries, butter smooth. and the tool calling, the one thing that quietly breaks most local setups, works here like it's nothing. it's not the model that's flaky, it's the harness around it. hermes agent is the first agent i've run that actually gets that right. one url, one local model on one card, and it runs like a wild horse.
1:46

small local model that falls apart in bloated agents like openclaw just runs like a wild horse in hermes agent. and that's not even my line, someone else called it that, i've just been quietly pointing people at this harness for months because it held up on everything i threw at it, 3b models all the way to one trillion params. watch this happen on my own machine. i pointed hermes agent at a local http endpoint, gemma 4 12b on my 3090 llama.cpp server, and it auto-detected the model and started working immediately. no config wrestling, no broken tool calls, no babysitting the output format, i typed in a url and it just went. the whole clip is exactly that, start to finish, no errors, no retries, butter smooth. and the tool calling, the one thing that quietly breaks most local setups, works here like it's nothing. it's not the model that's flaky, it's the harness around it. hermes agent is the first agent i've run that actually gets that right. one url, one local model on one card, and it runs like a wild horse.

Sudo su

27,339 views • 4 months ago

THIS $1,300 CARD HAS THE SAME 32GB OF VRAM AS A $2,000+ RTX 5090 - FOR LOCAL AI, THAT'S THE SPEC THAT DECIDES EVERYTHING. that clip is the gigabyte radeon ai pro r9700 ai top, 32gb of vram, built for local ai. the pitch is simple: the same memory capacity as an rtx 5090, for roughly a third of what a 5090 actually sells for. here's why that matters, and where it doesn't. for ai, vram is the gate. a model either fits in memory or it doesn't. 32gb loads models a 16gb card can't touch, full stop. so for running local llms and image models, this card does the one thing that counts, cheap. honest line: this is not a 5090 for gaming. the 5090 is far faster at raster and ray tracing. they only match on how much vram they carry. if you want frames, buy the 5090. if you want to fit big models locally, you just found the same 32gb for a third of the money. no $2,000+ price tag, no cloud gpu rental, no model too big for 16gb. the uncomfortable part isn't that amd is cheaper. it's that for local ai you were about to overpay for gaming power you'd never use. follow RetroChainer for more on paying for the spec that matters, and bookmark this before your next gpu.
1:52

THIS $1,300 CARD HAS THE SAME 32GB OF VRAM AS A $2,000+ RTX 5090 - FOR LOCAL AI, THAT'S THE SPEC THAT DECIDES EVERYTHING. that clip is the gigabyte radeon ai pro r9700 ai top, 32gb of vram, built for local ai. the pitch is simple: the same memory capacity as an rtx 5090, for roughly a third of what a 5090 actually sells for. here's why that matters, and where it doesn't. for ai, vram is the gate. a model either fits in memory or it doesn't. 32gb loads models a 16gb card can't touch, full stop. so for running local llms and image models, this card does the one thing that counts, cheap. honest line: this is not a 5090 for gaming. the 5090 is far faster at raster and ray tracing. they only match on how much vram they carry. if you want frames, buy the 5090. if you want to fit big models locally, you just found the same 32gb for a third of the money. no $2,000+ price tag, no cloud gpu rental, no model too big for 16gb. the uncomfortable part isn't that amd is cheaper. it's that for local ai you were about to overpay for gaming power you'd never use. follow RetroChainer for more on paying for the spec that matters, and bookmark this before your next gpu.

RetroChainer

38,844 views • 1 month ago

UC Berkeley just open-sourced FreeToken. (2–4x faster local LLM inference than Ollama) the results are wild: - Qwen3.6-35B on an 8GB GPU at 39.3 tokens/s - DeepSeek-V4-Flash 284B on a 32GB GPU at 22 tokens/s - GLM-5.2 753B on a 96GB GPU at 14.9 tokens/s a 35B model at 16-bit precision needs about 70GB just for its weights. even at 4 bits it is close to 18GB, and FreeToken serves it on an 8GB GPU. let me explain how: all three models mentioned above are Mixture-of-Experts, and that is what FreeToken takes advantage of. each layer holds hundreds of separate experts plus a small router that picks a few of them per token. Qwen3.6-35B activates roughly 3B of its 35B parameters per token. DeepSeek-V4-Flash picks 6 of 256 experts per layer, so 13B of its 284B run at a time. so compute was never the bottleneck. the weights a single step touches fit comfortably on a consumer GPU. every expert the router might pick still has to exist somewhere. they sit in system RAM, and the GPU keeps a cache of the ones the model has been using recently. so everything comes down to what happens when the router picks an expert that is not on the GPU. there are two ways to serve that miss: 1. copy it over PCIe and run it on the GPU 2. run it on the CPU, where it already lives both read from the same system memory, so they compete for one pool of bandwidth instead of adding to each other. existing engines pick one option and freeze it when the model loads. but routing changes on every token, so a fixed choice misses most of what the model asks for. FreeToken measures both bandwidths on your machine and splits each step's misses between the two paths in proportion. the GPU and CPU results then merge exactly, with no approximation. two machines with the same GPU can end up wanting opposite strategies, which I did not expect. a 5090 in a gaming desktop should push nearly everything over PCIe, while an 8GB laptop is better off computing most misses on the CPU. none of that is readable off a spec sheet, so the engine profiles it once per machine. the second half of the design is about agents. coding agents constantly rewrite their own history, and every edit normally forces thousands of tokens back through prefill. FreeToken saves its checkpoints at the exact boundaries agent frameworks cut on, so it only reprocesses the new part. its slowest first token stays under 44 seconds, while llama.cpp peaks at 232 and KTransformers at 946. it serves the OpenAI and Anthropic APIs under Apache 2.0, so Claude Code and Codex can point at it directly. releasing weights publicly decides who can download a model, not who can afford to run one. frontier open models keep shipping, and running them still assumes a rented cluster. meanwhile there are over a hundred million consumer machines with discrete GPUs sitting mostly idle. closing that gap was never a hardware problem, and work like this is what turns open weights into something you can actually use. paper: repo: almost every idea in this post, from why memory bandwidth decides the outcome to why moving weights costs more than computing on them, comes straight out of how a GPU is built. I wrote a detailed primer on that. the article is quoted below.
0:42

UC Berkeley just open-sourced FreeToken. (2–4x faster local LLM inference than Ollama) the results are wild: - Qwen3.6-35B on an 8GB GPU at 39.3 tokens/s - DeepSeek-V4-Flash 284B on a 32GB GPU at 22 tokens/s - GLM-5.2 753B on a 96GB GPU at 14.9 tokens/s a 35B model at 16-bit precision needs about 70GB just for its weights. even at 4 bits it is close to 18GB, and FreeToken serves it on an 8GB GPU. let me explain how: all three models mentioned above are Mixture-of-Experts, and that is what FreeToken takes advantage of. each layer holds hundreds of separate experts plus a small router that picks a few of them per token. Qwen3.6-35B activates roughly 3B of its 35B parameters per token. DeepSeek-V4-Flash picks 6 of 256 experts per layer, so 13B of its 284B run at a time. so compute was never the bottleneck. the weights a single step touches fit comfortably on a consumer GPU. every expert the router might pick still has to exist somewhere. they sit in system RAM, and the GPU keeps a cache of the ones the model has been using recently. so everything comes down to what happens when the router picks an expert that is not on the GPU. there are two ways to serve that miss: 1. copy it over PCIe and run it on the GPU 2. run it on the CPU, where it already lives both read from the same system memory, so they compete for one pool of bandwidth instead of adding to each other. existing engines pick one option and freeze it when the model loads. but routing changes on every token, so a fixed choice misses most of what the model asks for. FreeToken measures both bandwidths on your machine and splits each step's misses between the two paths in proportion. the GPU and CPU results then merge exactly, with no approximation. two machines with the same GPU can end up wanting opposite strategies, which I did not expect. a 5090 in a gaming desktop should push nearly everything over PCIe, while an 8GB laptop is better off computing most misses on the CPU. none of that is readable off a spec sheet, so the engine profiles it once per machine. the second half of the design is about agents. coding agents constantly rewrite their own history, and every edit normally forces thousands of tokens back through prefill. FreeToken saves its checkpoints at the exact boundaries agent frameworks cut on, so it only reprocesses the new part. its slowest first token stays under 44 seconds, while llama.cpp peaks at 232 and KTransformers at 946. it serves the OpenAI and Anthropic APIs under Apache 2.0, so Claude Code and Codex can point at it directly. releasing weights publicly decides who can download a model, not who can afford to run one. frontier open models keep shipping, and running them still assumes a rented cluster. meanwhile there are over a hundred million consumer machines with discrete GPUs sitting mostly idle. closing that gap was never a hardware problem, and work like this is what turns open weights into something you can actually use. paper: repo: almost every idea in this post, from why memory bandwidth decides the outcome to why moving weights costs more than computing on them, comes straight out of how a GPU is built. I wrote a detailed primer on that. the article is quoted below.

Akshay 🚀

344,501 views • 1 month ago

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

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

62,381 views • 3 months ago

this is a laptop running a 31b parameter model at 99% gpu autonomously through hermes agent, 15 tok/s sustained, 22.8 of 24gb vram gone, 94 watts at 50c. no api keys. no rate limits. no "your prompts are being used for training". no monthly subscription. no anthropic telling me what i can and cant ask. no openai logging my work. no outages when aws goes down. just google deepmind's open weights, open source llama.cpp, nous research's hermes agent, a rog scar 18 on my desk, and 95 watts of sustained compute while it builds stuff on its own. the laptop is roaring. results incoming.
0:50

this is a laptop running a 31b parameter model at 99% gpu autonomously through hermes agent, 15 tok/s sustained, 22.8 of 24gb vram gone, 94 watts at 50c. no api keys. no rate limits. no "your prompts are being used for training". no monthly subscription. no anthropic telling me what i can and cant ask. no openai logging my work. no outages when aws goes down. just google deepmind's open weights, open source llama.cpp, nous research's hermes agent, a rog scar 18 on my desk, and 95 watts of sustained compute while it builds stuff on its own. the laptop is roaring. results incoming.

Sudo su

65,567 views • 5 months ago

got gemma 4 31B with MTP running on my DGX Spark. Hermes Agent did most of the legwork. baseline vs MTP on GB10: • c=1: 3.65 → 6.37 tok/s (1.74x) • c=4: 14.34 → 23.59 tok/s (1.65x) • c=8: 14.37 → 24.18 tok/s (1.68x) google says "up to 2x" — we're not quite there but it's real, not vapor. stack: DGX Spark / GB10 + gemma-4-31b-it + gemma-4-31b-it-assistant (MTP drafter) + vLLM built from PR 41745 MTP is basically a lightweight draft model that predicts multiple tokens while the big model verifies them all at once. smaller model does the busywork, bigger model just says yes/no. simple idea, weird to implement. next: tune the draft block size and see if we can push past 2x. also want to try it with Hermes Agent feeding prompts end to end. p.s: this was all done from telegram. Google DeepMind NVIDIA AI Developer
0:22

got gemma 4 31B with MTP running on my DGX Spark. Hermes Agent did most of the legwork. baseline vs MTP on GB10: • c=1: 3.65 → 6.37 tok/s (1.74x) • c=4: 14.34 → 23.59 tok/s (1.65x) • c=8: 14.37 → 24.18 tok/s (1.68x) google says "up to 2x" — we're not quite there but it's real, not vapor. stack: DGX Spark / GB10 + gemma-4-31b-it + gemma-4-31b-it-assistant (MTP drafter) + vLLM built from PR 41745 MTP is basically a lightweight draft model that predicts multiple tokens while the big model verifies them all at once. smaller model does the busywork, bigger model just says yes/no. simple idea, weird to implement. next: tune the draft block size and see if we can push past 2x. also want to try it with Hermes Agent feeding prompts end to end. p.s: this was all done from telegram. Google DeepMind NVIDIA AI Developer

Joey

23,088 views • 5 months ago