Loading video...

Video Failed to Load

Go Home

INCREDIBLE SPEED running Claude Code w/ local models on my own GPUs at home > SGLang serving MiniMax-M2.1 > on 8x RTX 3090s > nvtop showing live GPU load > Claude Code generating code + docs > end-2-end on my AI cluster MiniMax-M2.1 is my favorite model to run...

TheAhmadOsman's profile picture

Ahmad

59,655 subscribers

592,866 views • 5 months ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

running Claude Code w/ local models on my own GPUs at home > vLLM serving GLM-4.5 Air > on 4x RTX 3090s > nvtop showing live GPU load > Claude Code generating code + docs > end-to-end on my AI cluster this is what local AI actually looks like Buy a GPU
1:57

running Claude Code w/ local models on my own GPUs at home > vLLM serving GLM-4.5 Air > on 4x RTX 3090s > nvtop showing live GPU load > Claude Code generating code + docs > end-to-end on my AI cluster this is what local AI actually looks like Buy a GPU

Ahmad

262,090 views • 6 months ago

We just built Figma for Claude Code > Select any element on your local front-end > Edit it like you would in Figma > Apply the changes with Claude Code This is not a demo or waitlist. Try it today.
0:22

We just built Figma for Claude Code > Select any element on your local front-end > Edit it like you would in Figma > Apply the changes with Claude Code This is not a demo or waitlist. Try it today.

Quentin Romero Lauro

250,872 views • 5 months ago

🚨 Kimi K2.7-Code is actually insane >#1 on Program Bench >#1 on MLS-Bench Lite (multi-step ML research) >Refreshing to see honest benchmarks instead of cherry-picked After claude fable debacle i want OSS to win FR to save us from dystopian end
0:32

🚨 Kimi K2.7-Code is actually insane >#1 on Program Bench >#1 on MLS-Bench Lite (multi-step ML research) >Refreshing to see honest benchmarks instead of cherry-picked After claude fable debacle i want OSS to win FR to save us from dystopian end

Chetaslua

37,602 views • 1 month ago

Thanks for the mention TBPN! We're working on making this run at >40 tok/sec on 2 Mac Studios (the full, unquantized Kimi K2.5). I'm already running Kimi K2.5 myself locally with Claude Code and it's impressive - very close to Opus level.
0:21

Thanks for the mention TBPN! We're working on making this run at >40 tok/sec on 2 Mac Studios (the full, unquantized Kimi K2.5). I'm already running Kimi K2.5 myself locally with Claude Code and it's impressive - very close to Opus level.

Alex Cheema

40,471 views • 5 months ago

I made a Vox-style explainer about Tang Dynasty. Just one prompt, 100% AI / end to end. keyframes (Seedream 5.0 Pro) → animation (Omni Flash) → voice (xAI TTS) → music (MiniMax Music 2.6) → assembled locally on Claude Code. The whole pipeline is on Atlas Cloud. One topic in, finished film out.
0:29

I made a Vox-style explainer about Tang Dynasty. Just one prompt, 100% AI / end to end. keyframes (Seedream 5.0 Pro) → animation (Omni Flash) → voice (xAI TTS) → music (MiniMax Music 2.6) → assembled locally on Claude Code. The whole pipeline is on Atlas Cloud. One topic in, finished film out.

Alisa Qian

107,847 views • 7 days ago

All soft bodies -> single drawcall. Hundreds of them -> 200 fps on my 3090. Trying to keep the code optimized in advance, because this game still has too many ways to waste gpu performance.
0:39

All soft bodies -> single drawcall. Hundreds of them -> 200 fps on my 3090. Trying to keep the code optimized in advance, because this game still has too many ways to waste gpu performance.

Zolden

14,119 views • 1 year ago

Let's be honest Claude Code was not working good with local LLMs. So, I Tried using OpenCode with LM Studio using Qwen 3.5 9B model on my RTX 5080 GPU. It's very usable and much faster than Claude Code. I'm actually planning to use this setup to build an entire vibe coded SaaS
2:31

Let's be honest Claude Code was not working good with local LLMs. So, I Tried using OpenCode with LM Studio using Qwen 3.5 9B model on my RTX 5080 GPU. It's very usable and much faster than Claude Code. I'm actually planning to use this setup to build an entire vibe coded SaaS

Tushar Verma

137,536 views • 4 months ago

You can use a 100% open source and MUCH cheaper/free alternative to Claude Code and Opus 4.5 OpenCode + MiniMax M2.1 can even build a 3D website using pure vibe coding. Steps are really simple: 1. Install OpenCode using the command 'npm i -g opencode-ai' 2. Get your MiniMax API key here: 3. Configure the MiniMax (official) mode Just type "opencode connect minimax" Coding plans start at $2… 10x cheaper than Claude Code (yes). You can also invite friends so they can get 10% off and you’ll get 10% API credits. (You can also use it locally if you have the config) And you're ready to build and iterate almost endlessly since the model is both way faster and cheaper than Opus in CC.
12:07

You can use a 100% open source and MUCH cheaper/free alternative to Claude Code and Opus 4.5 OpenCode + MiniMax M2.1 can even build a 3D website using pure vibe coding. Steps are really simple: 1. Install OpenCode using the command 'npm i -g opencode-ai' 2. Get your MiniMax API key here: 3. Configure the MiniMax (official) mode Just type "opencode connect minimax" Coding plans start at $2… 10x cheaper than Claude Code (yes). You can also invite friends so they can get 10% off and you’ll get 10% API credits. (You can also use it locally if you have the config) And you're ready to build and iterate almost endlessly since the model is both way faster and cheaper than Opus in CC.

Paul Couvert

42,443 views • 6 months ago

> This is historic, OS ChatGPT moment for the phone industry > A 9B phone use model from Z.ai is get things done on my phone > No need for an AGI scale model, no black box API. > Open-weight, open-code, open-future. > Community contribution welcome! Give it a try! Link👇
0:56

> This is historic, OS ChatGPT moment for the phone industry > A 9B phone use model from Z.ai is get things done on my phone > No need for an AGI scale model, no black box API. > Open-weight, open-code, open-future. > Community contribution welcome! Give it a try! Link👇

Tiezhen WANG

80,412 views • 7 months ago

Claude Code Full Sandbox Escape (CVE-2026-55607) writeup: prompt injection -> code execution on the host. works even in read-only permissions mode + full sandbox (it could be my Pwn2Own bug, but p2o was weird this year lol)
0:41

Claude Code Full Sandbox Escape (CVE-2026-55607) writeup: prompt injection -> code execution on the host. works even in read-only permissions mode + full sandbox (it could be my Pwn2Own bug, but p2o was weird this year lol)

vladimir metnew

99,173 views • 21 days ago

IT'S LIVE!!! go build apps w/ claude code opus 4.5 - visually 📌 just built MY very own pinterest - 0 API tokens - 0 confusing cursor - 0 bankruptcy on Lovable - back-end do-able too :) :) :) :)
0:47

IT'S LIVE!!! go build apps w/ claude code opus 4.5 - visually 📌 just built MY very own pinterest - 0 API tokens - 0 confusing cursor - 0 bankruptcy on Lovable - back-end do-able too :) :) :) :)

Daniel Ch

68,727 views • 6 months ago

🚀 New on ModelScope: MiniMax M2.1 is open-source! ✅ SOTA in 8+ languages (Rust, Go, Java, C++, TS, Kotlin, Obj-C, JS) ✅ Full-stack Web & mobile dev: Android/iOS, 3D visuals, vibe coding that actually ships ✅ Smarter, faster, 30% fewer tokens — with lightning mode (M2.1-lightning) for high-TPS workflows ✅ Top-tier on SWE-bench, VIBE, and custom coding/review benchmarks ✅ Works flawlessly in Cursor, Cline, Droid, BlackBox, and more It’s not just “better code” — it’s AI-native development, end to end. 🔗 Model:
0:54

🚀 New on ModelScope: MiniMax M2.1 is open-source! ✅ SOTA in 8+ languages (Rust, Go, Java, C++, TS, Kotlin, Obj-C, JS) ✅ Full-stack Web & mobile dev: Android/iOS, 3D visuals, vibe coding that actually ships ✅ Smarter, faster, 30% fewer tokens — with lightning mode (M2.1-lightning) for high-TPS workflows ✅ Top-tier on SWE-bench, VIBE, and custom coding/review benchmarks ✅ Works flawlessly in Cursor, Cline, Droid, BlackBox, and more It’s not just “better code” — it’s AI-native development, end to end. 🔗 Model:

ModelScope

16,939 views • 6 months ago

You can run a free and open-source alternative to Claude Code locally on your laptop! - Local AI model w/ Qwen3 Coder - Runs on your machine w/ LM Studio - Open-source VS Code extension w/ Cline Completely private (offline) and unlimited Setup and how it works: 00:00 Intro 01:11 LM Studio 02:10 Local AI model 03:38 Load the model 05:09 Start the server 05:33 Setup Cline 07:20 Prompt & example 09:02 Developer logs 10:12 Result reveal
11:34

You can run a free and open-source alternative to Claude Code locally on your laptop! - Local AI model w/ Qwen3 Coder - Runs on your machine w/ LM Studio - Open-source VS Code extension w/ Cline Completely private (offline) and unlimited Setup and how it works: 00:00 Intro 01:11 LM Studio 02:10 Local AI model 03:38 Load the model 05:09 Start the server 05:33 Setup Cline 07:20 Prompt & example 09:02 Developer logs 10:12 Result reveal

Paul Couvert

72,498 views • 9 months ago

Maximizing your token throughput is one of the biggest productivity unlocks in Claude Code. So here's my guide to use multiple Claude Codes at the same time, effectively: - Run multiple Claude Code sessions at the same time, each on a different feature (Ghostty is great for this) - Use Claude Code's built in git worktrees to keep each instance isolated on its own branch (-w or --worktree flag) - Let Claude handle creating PRs or merging the worktree branches when you're done - Use the Claude Code Desktop app as your multi-agent control center Full guide below:
2:44

Maximizing your token throughput is one of the biggest productivity unlocks in Claude Code. So here's my guide to use multiple Claude Codes at the same time, effectively: - Run multiple Claude Code sessions at the same time, each on a different feature (Ghostty is great for this) - Use Claude Code's built in git worktrees to keep each instance isolated on its own branch (-w or --worktree flag) - Let Claude handle creating PRs or merging the worktree branches when you're done - Use the Claude Code Desktop app as your multi-agent control center Full guide below:

Avthar

10,723 views • 3 months ago

FIRST STREAM ON METAWIN.COM INSTANT $4-->$4,000 FIST OF DESTRUCTION CAME TO PLAY $100 GIVEAWAY FOR PEOPLE WHO LIKE,RT, & TAG 2 FRIENDS GLGL P.S SIGN UP ON META ON MY CODE
0:30

FIRST STREAM ON METAWIN.COM INSTANT $4-->$4,000 FIST OF DESTRUCTION CAME TO PLAY $100 GIVEAWAY FOR PEOPLE WHO LIKE,RT, & TAG 2 FRIENDS GLGL P.S SIGN UP ON META ON MY CODE

ice.SOL🧊 |$10k+ GWs

13,404 views • 9 months ago

NVIDIA just dropped free API keys for every top AI model You don't need your own GPU and you don't pay per token. GLM-5.2, MiniMax, Kimi, DeepSeek, OpenAI, all running on NVIDIA's servers, called through a normal API. Link: How to use one: 1. Create a free NVIDIA account. 2. Pick a Free Endpoint model and open its Build tab. You'll see ready-to-copy code with the base URL 3. Hit Generate API Key, copy it and paste that base URL and key into Claude Code, Cursor, or Cline. Bonus: NVIDIA also dropped 237 official skills that install into Claude Code and Codex in one command. Bookmark this.
0:24

NVIDIA just dropped free API keys for every top AI model You don't need your own GPU and you don't pay per token. GLM-5.2, MiniMax, Kimi, DeepSeek, OpenAI, all running on NVIDIA's servers, called through a normal API. Link: How to use one: 1. Create a free NVIDIA account. 2. Pick a Free Endpoint model and open its Build tab. You'll see ready-to-copy code with the base URL 3. Hit Generate API Key, copy it and paste that base URL and key into Claude Code, Cursor, or Cline. Bonus: NVIDIA also dropped 237 official skills that install into Claude Code and Codex in one command. Bookmark this.

Yarchi

59,410 views • 9 days ago

I did a quick and dirty port of some python Asteroids code to adapt it to my USB->HP bridge, and here it is displaying on the HP1345 vector monitor!
0:25

I did a quick and dirty port of some python Asteroids code to adapt it to my USB->HP bridge, and here it is displaying on the HP1345 vector monitor!

Dave W Plummer

23,257 views • 5 months ago

Is your AI model losing focus on long tasks? Theo’s live stream showed Minimax M2.1 is built different, already outperforming other models that crumble under pressure. He had it grind on a feature for 400+ lines of code over 20 minutes without a single issue, while other models were making junior mistakes. It just plans, executes, and figures itself out. This is the kind of long-form consistency and reliability that most models only dream of. It’s fast, it’s solid, and it doesn’t lose track of instructions, a true workhorse for serious developers. Huge props to MiniMax (official) for building a model that can actually go the distance. See the future of AI development:
0:29

Is your AI model losing focus on long tasks? Theo’s live stream showed Minimax M2.1 is built different, already outperforming other models that crumble under pressure. He had it grind on a feature for 400+ lines of code over 20 minutes without a single issue, while other models were making junior mistakes. It just plans, executes, and figures itself out. This is the kind of long-form consistency and reliability that most models only dream of. It’s fast, it’s solid, and it doesn’t lose track of instructions, a true workhorse for serious developers. Huge props to MiniMax (official) for building a model that can actually go the distance. See the future of AI development:

FELIX

49,166 views • 6 months ago

If you use Claude Code, install this immediately. It's called Claude Code Templates. It adds an entire ecosystem of AI tools to Claude. Here's what you get: 1. Agent Teams Visual dashboards showing how multiple AI agents collaborate on code. 2. Specialized Agents Front-end developers, backend engineers, QA testers, marketers. 3. MCP Integrations Connect Claude to external tools and workflows. 4. Real-Time Monitoring Track AI development sessions and performance analytics. 5. Automation Scheduling Run tasks automatically every day. Example: You can schedule an agent team to run daily at 5AM. It researches trends, generates content, and builds workflows. All automatically. The best part? Everything is free and open source.
9:25

If you use Claude Code, install this immediately. It's called Claude Code Templates. It adds an entire ecosystem of AI tools to Claude. Here's what you get: 1. Agent Teams Visual dashboards showing how multiple AI agents collaborate on code. 2. Specialized Agents Front-end developers, backend engineers, QA testers, marketers. 3. MCP Integrations Connect Claude to external tools and workflows. 4. Real-Time Monitoring Track AI development sessions and performance analytics. 5. Automation Scheduling Run tasks automatically every day. Example: You can schedule an agent team to run daily at 5AM. It researches trends, generates content, and builds workflows. All automatically. The best part? Everything is free and open source.

Julian Goldie SEO

107,015 views • 4 months ago

I just found a way to use Claude Code completely free. Claude Code is Anthropic’s terminal coding agent that usually needs a paid API key to run. But a viral GitHub project called Free Claude Code, now sitting at 37k stars, lets you skip the billing entirely. It works as a tiny proxy that sits between Claude Code and free model providers like NVIDIA NIM, OpenRouter, DeepSeek, and Gemini. Every request Claude Code would send to Anthropic gets quietly rerouted to a free model on the other side. The interface stays the same. What’s actually thinking behind it changes. Setup takes a couple of quick commands and a free API key from NVIDIA NIM or OpenRouter. Paste it into the local dashboard, pick a model, and you’re building. The catch is you’re not really using Claude anymore. But when the code ships, does the model badge matter? -- I have shared the Github Link in my free Whatsapp Community ↓
0:36

I just found a way to use Claude Code completely free. Claude Code is Anthropic’s terminal coding agent that usually needs a paid API key to run. But a viral GitHub project called Free Claude Code, now sitting at 37k stars, lets you skip the billing entirely. It works as a tiny proxy that sits between Claude Code and free model providers like NVIDIA NIM, OpenRouter, DeepSeek, and Gemini. Every request Claude Code would send to Anthropic gets quietly rerouted to a free model on the other side. The interface stays the same. What’s actually thinking behind it changes. Setup takes a couple of quick commands and a free API key from NVIDIA NIM or OpenRouter. Paste it into the local dashboard, pick a model, and you’re building. The catch is you’re not really using Claude anymore. But when the code ships, does the model badge matter? -- I have shared the Github Link in my free Whatsapp Community ↓

Vaibhav Sisinty

36,419 views • 15 days ago