Loading video...

Video Failed to Load

Go Home

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...

sudoingX's profile picture

Sudo su

26,228 subscribers

65,567 views • 1 month ago •via X (Twitter)

News & PoliticsEducationScience & 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 with a beautiful WebUI. No Telegram bot. No API keys. No setup. Plus, your AI agent is live in 60 seconds. This is FlyHermes.
0:41

Hermes Agent with a beautiful WebUI. No Telegram bot. No API keys. No setup. Plus, your AI agent is live in 60 seconds. This is FlyHermes.

Antoine Rousseaux

25,909 views • 2 months ago

HERMES AGENT CAN NOW RUN COMPLETELY FREE WITH GEMMA 4 + OLLAMA. No API bills, no limits, and a 256k context window running straight from your own machine.
7:33

HERMES AGENT CAN NOW RUN COMPLETELY FREE WITH GEMMA 4 + OLLAMA. No API bills, no limits, and a 256k context window running straight from your own machine.

0xMarioNawfal

120,520 views • 2 months ago

We deployed a fully private AI agent on NuNet in under 5 minutes 🚀 OpenClaw🦞 running Qwen through ollama , one of the hottest open source model families right now, entirely on decentralized compute. No cloud. No API keys. No data leaving the machine. This is what private AI looks like when you actually build it instead of just talking about it. Your model. Your hardware. Your rules. Full walkthrough showing exactly how it works: What should we deploy next?
12:59

We deployed a fully private AI agent on NuNet in under 5 minutes 🚀 OpenClaw🦞 running Qwen through ollama , one of the hottest open source model families right now, entirely on decentralized compute. No cloud. No API keys. No data leaving the machine. This is what private AI looks like when you actually build it instead of just talking about it. Your model. Your hardware. Your rules. Full walkthrough showing exactly how it works: What should we deploy next?

NuNet 🌐

87,487 views • 2 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 • 1 month ago

Open-source just won... Agent S2 is an AI agent that uses your computer like a human. → No fake demos → No terminal hallucinations → Just real results and it’s FREE. Here’s why this is the future of work: 👇
0:38

Open-source just won... Agent S2 is an AI agent that uses your computer like a human. → No fake demos → No terminal hallucinations → Just real results and it’s FREE. Here’s why this is the future of work: 👇

Shruti

206,593 views • 1 year ago

OK it's a game changer You can create and run an AI agent 100% locally on your laptop. No need to connect or pay a provider like OpenAI or Anthropic. Combine the open source Google Gemma 3 model, Smolagents and LM Studio and you're ready. (Links and resources below) #gifted
17:24

OK it's a game changer You can create and run an AI agent 100% locally on your laptop. No need to connect or pay a provider like OpenAI or Anthropic. Combine the open source Google Gemma 3 model, Smolagents and LM Studio and you're ready. (Links and resources below) #gifted

Paul Couvert

78,710 views • 1 year 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

70,583 views • 2 months ago

When your tool is open source and free, your creativity has no ceiling. The ComfyUI skill in Nous Research Hermes Agent lets you compose sophisticated workflows by chatting to an agent. Try it today.
0:20

When your tool is open source and free, your creativity has no ceiling. The ComfyUI skill in Nous Research Hermes Agent lets you compose sophisticated workflows by chatting to an agent. Try it today.

ComfyUI

162,762 views • 1 month ago

Introducing Agent Cookie. 🥷🏻🍪 For anyone running OpenClaw🦞 or Nous Research's Hermes on a Mac mini: I kept finding my agent logged out of everything, and it sucked. So I fixed it. "Add this to my Amazon cart." Sorry, logged out again. "Order my usual on Instacart." Nope, not logged in anymore. The fix: your laptop's cookies, CLI tokens, and API keys sync to your Mac mini. Continuously. Encrypted end-to-end over your Tailscale tailnet. No logging in twice. 🌐
1:49

Introducing Agent Cookie. 🥷🏻🍪 For anyone running OpenClaw🦞 or Nous Research's Hermes on a Mac mini: I kept finding my agent logged out of everything, and it sucked. So I fixed it. "Add this to my Amazon cart." Sorry, logged out again. "Order my usual on Instacart." Nope, not logged in anymore. The fix: your laptop's cookies, CLI tokens, and API keys sync to your Mac mini. Continuously. Encrypted end-to-end over your Tailscale tailnet. No logging in twice. 🌐

Matt Van Horn

252,424 views • 10 days ago

I thought I needed a powerful GPU to run serious AI locally. I was completely wrong. Late 2025, Ollama quietly launched something that changed everything. They built a cloud inference layer running on NVIDIA's Blackwell architecture, the most powerful GPU hardware available today. No GPU on your desk required. No expensive API subscription. No complex setup. Just one command and you're running Kimi K2.5, a 1 trillion parameter open-source model, completely free. I connected it to OpenClaw, which links my phone's messaging apps to the AI agent running at home. I sent a message from WhatsApp. My machine picked it up, ran the task, and sent me back the result. It felt like magic. It's just good engineering. Save this post, you'll want this when you're building your first workflow. Want the SOP? DM me.
9:21

I thought I needed a powerful GPU to run serious AI locally. I was completely wrong. Late 2025, Ollama quietly launched something that changed everything. They built a cloud inference layer running on NVIDIA's Blackwell architecture, the most powerful GPU hardware available today. No GPU on your desk required. No expensive API subscription. No complex setup. Just one command and you're running Kimi K2.5, a 1 trillion parameter open-source model, completely free. I connected it to OpenClaw, which links my phone's messaging apps to the AI agent running at home. I sent a message from WhatsApp. My machine picked it up, ran the task, and sent me back the result. It felt like magic. It's just good engineering. Save this post, you'll want this when you're building your first workflow. Want the SOP? DM me.

Julian Goldie SEO

11,967 views • 2 months ago

🚨 Claude Code just got REPLACED overnight… for $0 An open-source project is now running a 122B model locally on your MacBook 🤯 No API fees. No cloud. No limits. Just raw power on your own machine. 1 command install. Double-click to launch. If this works at scale… it’s game over for paid AI tools. GitHub ↓
0:34

🚨 Claude Code just got REPLACED overnight… for $0 An open-source project is now running a 122B model locally on your MacBook 🤯 No API fees. No cloud. No limits. Just raw power on your own machine. 1 command install. Double-click to launch. If this works at scale… it’s game over for paid AI tools. GitHub ↓

Shruti Codes

40,266 views • 1 month ago

happy friday. sneak peek at some new features i'm building for the bankr agent: > sandboxed filesystem (your agent gets its own secure file system in the browser. you control what it can access. no agent running loose on your actual computer) > skill uploads (plugin new capabilities so your agent learns new things) > cli download & access > secure environment variables for api keys > github integration (connect your repo for reads and writes directly from your agent) all of this runs in a secure browser environment. no desktop app. no messy configuration. no downloading agent harnesses from the terminal. just a sandbox you control. in the video: i download an audit skill, run it against a smart contract, and save the report straight to the filesystem. then i ask the agent to pull all my 2026 transactions and write a csv for my accountant.
0:58

happy friday. sneak peek at some new features i'm building for the bankr agent: > sandboxed filesystem (your agent gets its own secure file system in the browser. you control what it can access. no agent running loose on your actual computer) > skill uploads (plugin new capabilities so your agent learns new things) > cli download & access > secure environment variables for api keys > github integration (connect your repo for reads and writes directly from your agent) all of this runs in a secure browser environment. no desktop app. no messy configuration. no downloading agent harnesses from the terminal. just a sandbox you control. in the video: i download an audit skill, run it against a smart contract, and save the report straight to the filesystem. then i ask the agent to pull all my 2026 transactions and write a csv for my accountant.

deployer

45,597 views • 2 months ago

Local. Open weights. Native 4K. LTX-2 is now a 100% Open Source AI video model, and I tested it on my rig! Installation, VRAM usage, and the prompts I used for this video, below 👇
0:41

Local. Open weights. Native 4K. LTX-2 is now a 100% Open Source AI video model, and I tested it on my rig! Installation, VRAM usage, and the prompts I used for this video, below 👇

TechHalla

34,466 views • 5 months ago

We’re excited to introduce Pocket TTS: a 100M-parameter text-to-speech model with high-quality voice cloning that runs on your laptop—no GPU required. Open-source, lightweight, and incredibly fast. 🧵👇
1:44

We’re excited to introduce Pocket TTS: a 100M-parameter text-to-speech model with high-quality voice cloning that runs on your laptop—no GPU required. Open-source, lightweight, and incredibly fast. 🧵👇

kyutai

235,651 views • 4 months ago

LFG! Nous Research's Hermes Agent is live on the Umbrel App Store! It's an AI agent that gets smarter the longer it runs, remembers stuff with persistent memory across sessions, learns your workflow, and autonomously creates its own reusable skills from experience. And it's sandboxed like every Umbrel app so it can't touch anything it's not supposed to. 1-click install. Login with ChatGPT, use an OpenRouter/OpenAI/Anthropic API key, or point it to a local Ollama model running on the same Umbrel.
1:22

LFG! Nous Research's Hermes Agent is live on the Umbrel App Store! It's an AI agent that gets smarter the longer it runs, remembers stuff with persistent memory across sessions, learns your workflow, and autonomously creates its own reusable skills from experience. And it's sandboxed like every Umbrel app so it can't touch anything it's not supposed to. 1-click install. Login with ChatGPT, use an OpenRouter/OpenAI/Anthropic API key, or point it to a local Ollama model running on the same Umbrel.

Umbrel ☂️

29,882 views • 1 month ago

A FULLY AUTONOMOUS AI AGENT RUNNING LOCALLY ON AN 8GB VRAM LAPTOP gemma 4 26b plus hermes agent from nous research, the integration with llama.cpp took 2 minutes now it writes and patches code, manages github repos, browses the web, schedules cron jobs and connects directly to notion and obsidian all offline, all local, intel i5 and any 8gb vram gpu is enough to run the whole thing 24/7 most people with an rtx 4060 are using it for games and have no idea it can run a developer plus system admin plus personal assistant rolled into one the full breakdown of what hardware runs what in 2026 is in the article below ↓
0:20

A FULLY AUTONOMOUS AI AGENT RUNNING LOCALLY ON AN 8GB VRAM LAPTOP gemma 4 26b plus hermes agent from nous research, the integration with llama.cpp took 2 minutes now it writes and patches code, manages github repos, browses the web, schedules cron jobs and connects directly to notion and obsidian all offline, all local, intel i5 and any 8gb vram gpu is enough to run the whole thing 24/7 most people with an rtx 4060 are using it for games and have no idea it can run a developer plus system admin plus personal assistant rolled into one the full breakdown of what hardware runs what in 2026 is in the article below ↓

leopardracer

33,348 views • 1 day ago

OpenClaw in your pocket — powered by Solana 🦞 (Video sent by one of our .molt domain users minting AI agent on Seeker | Solana Mobile ) Connect wallet → pick a name → mint → your AI agent is live. That's it. No servers, no CLI, no Docker, no monthly bills, no coding. Every .molt domain is an NFT with a built-in wallet, zero private keys, and full on-chain identity. One mint and you own an agent that can launch tokens, mint NFTs, host x402 services, and chat on Telegram, Discord & Slack. OpenClaw runs for free — persistent memory, sleeps when idle, wakes on demand. Your agent is always there when you need it. No $600 MacBook. No $15/month VPS. Just your phone and a Solana wallet. This is what building on Solana feels like — fast, cheap, and instant. A Solana Seeker phone with a built-in wallet is all you need. Mint your AI agent in seconds, straight from your pocket.
2:29

OpenClaw in your pocket — powered by Solana 🦞 (Video sent by one of our .molt domain users minting AI agent on Seeker | Solana Mobile ) Connect wallet → pick a name → mint → your AI agent is live. That's it. No servers, no CLI, no Docker, no monthly bills, no coding. Every .molt domain is an NFT with a built-in wallet, zero private keys, and full on-chain identity. One mint and you own an agent that can launch tokens, mint NFTs, host x402 services, and chat on Telegram, Discord & Slack. OpenClaw runs for free — persistent memory, sleeps when idle, wakes on demand. Your agent is always there when you need it. No $600 MacBook. No $15/month VPS. Just your phone and a Solana wallet. This is what building on Solana feels like — fast, cheap, and instant. A Solana Seeker phone with a built-in wallet is all you need. Mint your AI agent in seconds, straight from your pocket.

Molt.id

77,994 views • 3 months ago

i built a full game on a single GPU with a 3B model and this is the worst local AI will ever be. this was supposed to be a benchmark test. load the model, measure tokens per second, write it up, move on. instead i spent 20 minutes playing Octopus Invaders because the game is genuinely fun and i couldn't stop. a model with 3B active parameters built this from a single prompt. it debugged its own collision system when bullets were phasing through enemies. read the error, found the fix, kept building. this is not a frontier API. this is a quantized open source model running on hardware you can buy used for $800-$1200. no cloud. no subscription. no API costs. just a mass produced consumer GPU doing things that would have been absurd 12 months ago. and here's the part that should keep you up at night: every month the models get smaller and smarter. the quants get tighter. the context windows get longer. the tooling gets cleaner. what 3B active parameters does today on 24gb, a 1B model will do on 8gb within a year. you are looking at the floor. not the ceiling.
0:27

i built a full game on a single GPU with a 3B model and this is the worst local AI will ever be. this was supposed to be a benchmark test. load the model, measure tokens per second, write it up, move on. instead i spent 20 minutes playing Octopus Invaders because the game is genuinely fun and i couldn't stop. a model with 3B active parameters built this from a single prompt. it debugged its own collision system when bullets were phasing through enemies. read the error, found the fix, kept building. this is not a frontier API. this is a quantized open source model running on hardware you can buy used for $800-$1200. no cloud. no subscription. no API costs. just a mass produced consumer GPU doing things that would have been absurd 12 months ago. and here's the part that should keep you up at night: every month the models get smaller and smarter. the quants get tighter. the context windows get longer. the tooling gets cleaner. what 3B active parameters does today on 24gb, a 1B model will do on 8gb within a year. you are looking at the floor. not the ceiling.

Sudo su

36,251 views • 3 months ago

look anon, those of you who kept saying local AI is not there yet, who said open source can't compete, who said you need cloud APIs to get anything serious done, look at this gameplay for one minute. every pixel on this screen was written by one model, in one shot, on a single rtx 3090 with 24gb of vram. the model is qwen 3.6 27b dense q4. the harness is hermes agent. the hardware is a single consumer card you can buy used for 900 dollars. the prompt is open source on github. every claim verifiable, on your own desk. if your local AI take is from 2024, update it. the consumer tier is shipping work that was supposed to need 8 gpus and an api key. open source moved the floor while the rest of the field was busy explaining why it cannot. 24gb tier owners are eating ramen with half boiled egg and double chocolate.
1:39

look anon, those of you who kept saying local AI is not there yet, who said open source can't compete, who said you need cloud APIs to get anything serious done, look at this gameplay for one minute. every pixel on this screen was written by one model, in one shot, on a single rtx 3090 with 24gb of vram. the model is qwen 3.6 27b dense q4. the harness is hermes agent. the hardware is a single consumer card you can buy used for 900 dollars. the prompt is open source on github. every claim verifiable, on your own desk. if your local AI take is from 2024, update it. the consumer tier is shipping work that was supposed to need 8 gpus and an api key. open source moved the floor while the rest of the field was busy explaining why it cannot. 24gb tier owners are eating ramen with half boiled egg and double chocolate.

Sudo su

29,584 views • 29 days ago

🚨BREAKING: The "OpenClaw for video production" just dropped. It's called AIVideo Agent and it runs your entire content pipeline 24/7 entirely on its own. No API keys. No technical setup. No configuration screens. Just tell it what you want. It ships.
0:52

🚨BREAKING: The "OpenClaw for video production" just dropped. It's called AIVideo Agent and it runs your entire content pipeline 24/7 entirely on its own. No API keys. No technical setup. No configuration screens. Just tell it what you want. It ships.

Hasan Toor

231,081 views • 3 months ago