Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing local Reachy Mini conversations: free chats forever! So fast that we had to hardcode delays to stop it from interrupting you mid-sentence. We built an open-source Realtime API powered by llama.cpp: Parakeet -> Gemma 4 E4B -> Qwen3TTS Run it anywhere you run local LMs. Video shows DGX... show more

Andi Marafioti

8,473 subscribers

77,561 views • 3 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Local Reachy Mini conversations wireless looks like magic! You can bring your friend around the house and get WOW effect from anyone! 🔥 Thanks Andi Marafioti for the blog post on how to set this up: Open-source Realtime API powered by llama.cpp: Parakeet -> Gemma 4 E4B -> Qwen3TTS. Just perfect on M5! Pictures, audio and content remain local and private! Next step adding some tools to search on the web or even better interfacing with my Hermes Agent! 🔥

Local Reachy Mini conversations wireless looks like magic! You can bring your friend around the house and get WOW effect from anyone! 🔥 Thanks Andi Marafioti for the blog post on how to set this up: Open-source Realtime API powered by llama.cpp: Parakeet -> Gemma 4 E4B -> Qwen3TTS. Just perfect on M5! Pictures, audio and content remain local and private! Next step adding some tools to search on the web or even better interfacing with my Hermes Agent! 🔥

Ivan Fioravanti ᯅ

22,458 views • 3 months ago

Run OpenClaw 2.0 through Atomic Chat local LLM server on a 16GB MacBook 💻🦞 We gave OpenClaw a task to edit a video using Gemma 4 E4B, it successfully created a welcome video in two minutes by writing custom React code Load the model in start the LLM server and OpenClaw 2.0 picks it right up

Run OpenClaw 2.0 through Atomic Chat local LLM server on a 16GB MacBook 💻🦞 We gave OpenClaw a task to edit a video using Gemma 4 E4B, it successfully created a welcome video in two minutes by writing custom React code Load the model in start the LLM server and OpenClaw 2.0 picks it right up

atomic.chat

43,435 views • 3 days ago

You can run local AI models up to 120B without a $10,000 Mac Studio This phone-sized device is your own server for open-source models. 100% local and private. And you can use it to: - Power an agent like OpenClaw 24/7 - Completely replace a chatbot - Literally anything that requires an API It’s called Tiiny, and, once again, you can run the latest open-source models on it. Link below

You can run local AI models up to 120B without a $10,000 Mac Studio This phone-sized device is your own server for open-source models. 100% local and private. And you can use it to: - Power an agent like OpenClaw 24/7 - Completely replace a chatbot - Literally anything that requires an API It’s called Tiiny, and, once again, you can run the latest open-source models on it. Link below

Paul Couvert

41,245 views • 5 months ago

Introducing Loopany 🔁 Stop prompting, Design the loop. A loop management space that connects to your team’s own local agents: - Scaffold loop contracts, state, and logs - Add programmable triggers - Run self-improving cycles - Start from built-in loop templates We baked in everything we’ve learned from running loops inside our own team. Free and open source. Keen to hear your feedback:

Introducing Loopany 🔁 Stop prompting, Design the loop. A loop management space that connects to your team’s own local agents: - Scaffold loop contracts, state, and logs - Add programmable triggers - Run self-improving cycles - Start from built-in loop templates We baked in everything we’ve learned from running loops inside our own team. Free and open source. Keen to hear your feedback:

Jason Zhou

32,504 views • 1 month ago

Happily running Deepseek with unlimited tokens in OMP on 2 DGX Sparks. Yesterday I was explaining to someone about local ai and the power you have with it. He was so intrigued that you can run agents and workflows non stop and not pay anyone. That person was related to my boss. We will see what we build on prem.

Happily running Deepseek with unlimited tokens in OMP on 2 DGX Sparks. Yesterday I was explaining to someone about local ai and the power you have with it. He was so intrigued that you can run agents and workflows non stop and not pay anyone. That person was related to my boss. We will see what we build on prem.

Joey

16,883 views • 27 days ago

I have an AI employee doing work for me 24/7 for basically free You NEED to set this up It's Hermes Agent powered by local models on a @NVIDIA_AI_PC DGX Spark In this video I cover how to set up Hermes, load in Qwen 3.6, and have it work 24/7. NO experience required

I have an AI employee doing work for me 24/7 for basically free You NEED to set this up It's Hermes Agent powered by local models on a @NVIDIA_AI_PC DGX Spark In this video I cover how to set up Hermes, load in Qwen 3.6, and have it work 24/7. NO experience required

Alex Finn

93,381 views • 3 months ago

Databricks CEO Ali Ghodsi describes the difficulties of building a business around open source: "You have to hit two home runs, consecutively." "Your first home run - and you're banking on hitting that home run - is that your open source project takes over the world. Everybody wants to download it." If you don't hit that home run, Ali says, you just shot yourself in the foot. You just gave away your IP and got nothing back for it. But even if you hit this home run, you still don't have a monetizable business. You still can't make any money. So you have to hit the second home run: "You need a 10x innovation on top of the open source. That's the proprietary value you'll provide companies. That's why they'll come to you. Otherwise, they can get the open source anywhere." If you don't hit the second home run, the hyperscalers pick up your open source model, and they offer it for almost-free. "Getting into open source and monetizing is not an easy sport. Preferably don't get into it, because you might get hurt."

Databricks CEO Ali Ghodsi describes the difficulties of building a business around open source: "You have to hit two home runs, consecutively." "Your first home run - and you're banking on hitting that home run - is that your open source project takes over the world. Everybody wants to download it." If you don't hit that home run, Ali says, you just shot yourself in the foot. You just gave away your IP and got nothing back for it. But even if you hit this home run, you still don't have a monetizable business. You still can't make any money. So you have to hit the second home run: "You need a 10x innovation on top of the open source. That's the proprietary value you'll provide companies. That's why they'll come to you. Otherwise, they can get the open source anywhere." If you don't hit the second home run, the hyperscalers pick up your open source model, and they offer it for almost-free. "Getting into open source and monetizing is not an easy sport. Preferably don't get into it, because you might get hurt."

TBPN

45,393 views • 8 months ago

🎉 Introducing 𝙾𝚙𝚎𝚗 𝙱𝚘𝚝 An open source Grok Bot that works with ANY agent harness, designed for real companies. It includes: - AI Coworkers - Generative UI - Computer use (remote/local) - Agent-human handoffs - Full data recording, owned by you Repo → We're using this internally at CopilotKit🪁 and it's changing the way we work forever. Powered by CopilotKit and AG-UI. More info below 👇

🎉 Introducing 𝙾𝚙𝚎𝚗 𝙱𝚘𝚝 An open source Grok Bot that works with ANY agent harness, designed for real companies. It includes: - AI Coworkers - Generative UI - Computer use (remote/local) - Agent-human handoffs - Full data recording, owned by you Repo → We're using this internally at CopilotKit🪁 and it's changing the way we work forever. Powered by CopilotKit and AG-UI. More info below 👇

Atai Barkai

818,963 views • 16 days ago

built a dead simple chrome extension for my wife and myself. sharing here as free open source as usual Simple Words we find ourselves spending too much time wordsmithing our email replies, just to make sure we sound friendly and respectful this chrome extension is really simple and quite literally a gpt wrapper that only does one thing - one click turning what you mean to what's ready to send it runs on your own api key, subscription or local LLM. the extension itself is free and open source. if you tried it out, would be keen to hear how it works for you! extension: repo:

built a dead simple chrome extension for my wife and myself. sharing here as free open source as usual Simple Words we find ourselves spending too much time wordsmithing our email replies, just to make sure we sound friendly and respectful this chrome extension is really simple and quite literally a gpt wrapper that only does one thing - one click turning what you mean to what's ready to send it runs on your own api key, subscription or local LLM. the extension itself is free and open source. if you tried it out, would be keen to hear how it works for you! extension: repo:

Kun Chen

10,975 views • 3 months ago

Spent the last few days vibe coding on my NVIDIA DGX Spark. Here's what I learned. Qwen 3.5 122B took one minute and nine seconds to respond "Hi how are you doing". Unusable for vibe coding. Gemma 4 was fast but built a dot instead of a first person shooter game. GPT-OSS 120B was the sweet spot. Fast, capable, and actually produced working HTML. Open source models running locally are not replacing Claude Opus 4.6 or Codex with GPT 5.4. Not even close. But they're getting better every month. The new DGX Spark Bench is live on Real-world benchmarks for local models on local hardware. This is just the start. Full video below.

Spent the last few days vibe coding on my NVIDIA DGX Spark. Here's what I learned. Qwen 3.5 122B took one minute and nine seconds to respond "Hi how are you doing". Unusable for vibe coding. Gemma 4 was fast but built a dot instead of a first person shooter game. GPT-OSS 120B was the sweet spot. Fast, capable, and actually produced working HTML. Open source models running locally are not replacing Claude Opus 4.6 or Codex with GPT 5.4. Not even close. But they're getting better every month. The new DGX Spark Bench is live on Real-world benchmarks for local models on local hardware. This is just the start. Full video below.

BridgeMind

57,304 views • 4 months ago

For science, AI sovereignty and physics-grounded reasoning are non-negotiable. But how can we teach a small LLM like Gemma-4-E4B physics? One way is to use Agent Skills, but this has so far been limited to closed frontier models. mistral․rs now implements Agent Skills natively: the first self-hosted inference engine that does this as part of the local inference substrate, where we can use small models to solve complex scientific and other tasks in a flexible and scalable way. We are in a period of uncertainty about frontier models - access, pricing, deprecation, abrupt restriction. The good news is that when the entire stack runs locally we can build AI that is entirely your own: You own the weights, the skills, the execution loop, the data - all of it runs on your hardware and is reproducible and durable. While virtually all local inference engines expose a model behind an OpenAI-compatible endpoint, everything agentic is then assembled around it by an external orchestrator that injects context, manages tools, mounts files, and brokers execution. mistral․rs is natively agentic and moves that machinery into the server itself, allowing us to build complex agentic workflows and run them locally, on open-source models. With this new feature you can now upload Agent Skills bundles to /v1/skills, reference them from Responses API requests by identity, and run them inside a native agentic loop with persistent Python sessions, figure capture, sandboxed shell execution, file inputs mounted directly into the working session; plug-and-play and completely compatible with your existing code/workflow. A model with a native skill substrate can act, observe consequences, and can modify what it is able to do. The skill is retained procedural capability of the system. Attached is a short video of all of it: skills, code execution, the full agentic loop carried by Gemma-4-E4B; running entirely on my MacBook Pro. You can install and run a server with this capability in two lines in your terminal, with any quantization you need. Nice work by the Google Gemma team Logan Kilpatrick Demis Hassabis and Eric Buehler with mistral․rs!

For science, AI sovereignty and physics-grounded reasoning are non-negotiable. But how can we teach a small LLM like Gemma-4-E4B physics? One way is to use Agent Skills, but this has so far been limited to closed frontier models. mistral․rs now implements Agent Skills natively: the first self-hosted inference engine that does this as part of the local inference substrate, where we can use small models to solve complex scientific and other tasks in a flexible and scalable way. We are in a period of uncertainty about frontier models - access, pricing, deprecation, abrupt restriction. The good news is that when the entire stack runs locally we can build AI that is entirely your own: You own the weights, the skills, the execution loop, the data - all of it runs on your hardware and is reproducible and durable. While virtually all local inference engines expose a model behind an OpenAI-compatible endpoint, everything agentic is then assembled around it by an external orchestrator that injects context, manages tools, mounts files, and brokers execution. mistral․rs is natively agentic and moves that machinery into the server itself, allowing us to build complex agentic workflows and run them locally, on open-source models. With this new feature you can now upload Agent Skills bundles to /v1/skills, reference them from Responses API requests by identity, and run them inside a native agentic loop with persistent Python sessions, figure capture, sandboxed shell execution, file inputs mounted directly into the working session; plug-and-play and completely compatible with your existing code/workflow. A model with a native skill substrate can act, observe consequences, and can modify what it is able to do. The skill is retained procedural capability of the system. Attached is a short video of all of it: skills, code execution, the full agentic loop carried by Gemma-4-E4B; running entirely on my MacBook Pro. You can install and run a server with this capability in two lines in your terminal, with any quantization you need. Nice work by the Google Gemma team Logan Kilpatrick Demis Hassabis and Eric Buehler with mistral․rs!

Markus J. Buehler

10,229 views • 2 months ago

You really can just do things! Use *any* Hugging Face space as a MCP server along with your Local Models! 🔥 Here in we use Qwen 3 30B A3B with ggml llama.cpp and Hugging Face tiny agents to create images via FLUX powered by ZeroGPU ⚡ It's quite a bit crazy to see local models be capable of so much and just be able to understand/ infer from tool description! There's a lot of potential here in automating video generation workflows, content curation and a lot more.. Bonus: you can plug any other Inference Provider if you don't want to run locally too! npx @ huggingface/tiny-agents run [TASK] oh, and we provide both typescript and python client! 🐐

You really can just do things! Use any Hugging Face space as a MCP server along with your Local Models! 🔥 Here in we use Qwen 3 30B A3B with ggml llama.cpp and Hugging Face tiny agents to create images via FLUX powered by ZeroGPU ⚡ It's quite a bit crazy to see local models be capable of so much and just be able to understand/ infer from tool description! There's a lot of potential here in automating video generation workflows, content curation and a lot more.. Bonus: you can plug any other Inference Provider if you don't want to run locally too! npx @ huggingface/tiny-agents run [TASK] oh, and we provide both typescript and python client! 🐐

Vaibhav (VB) Srivastav

39,113 views • 1 year ago

Someone built a modern version of Notepad made specifically for Markdown. No setup, no account, opens instantly with an Obsidian meets VSCode feel but way lighter. → Writes and renders Markdown live so headers, lists and code blocks look right as you type → Optional local AI endpoint built in if you want it → Free and open source Obsidian is a whole system you commit to. Sometimes you just want to open a file, edit it and get out. This is exactly that.

Someone built a modern version of Notepad made specifically for Markdown. No setup, no account, opens instantly with an Obsidian meets VSCode feel but way lighter. → Writes and renders Markdown live so headers, lists and code blocks look right as you type → Optional local AI endpoint built in if you want it → Free and open source Obsidian is a whole system you commit to. Sometimes you just want to open a file, edit it and get out. This is exactly that.

0xMarioNawfal

62,785 views • 1 month ago

Built an open-source Jupyter Notebook that brings the power of OpenAI's code interpreter into your local Python development environment. Watch how easy it is to use Thread to edit code I wrote, chat with my notebook, or generate charts just using prompts. We built Thread using Next.js, Chakra and Project Jupyter and you can install it by running: pip install thread-dev

Built an open-source Jupyter Notebook that brings the power of OpenAI's code interpreter into your local Python development environment. Watch how easy it is to use Thread to edit code I wrote, chat with my notebook, or generate charts just using prompts. We built Thread using Next.js, Chakra and Project Jupyter and you can install it by running: pip install thread-dev

Ali Shobeiri

112,660 views • 2 years ago

HERMES CAN NOW RUN FOR FREE FOREVER A new Gemma 4 update just removed the biggest problem with local AI agents. The Upgrade: → Gemma 4 runs around 90% faster on Apple Silicon using Ollama + MLX → Plug it into Hermes with a few terminal commands → Run private agent workflows without subscriptions, token limits, or API bills What It Can Actually Do: ✓ Build and preview apps locally ✓ Use /learn to turn tutorials into permanent skills ✓ Read files, analyse landing pages, summarise emails, and track AI news ✓ Run loops until a task is complete instead of waiting for another prompt ✓ Launch multiple Gemma 4 subagents to work on separate tasks in parallel No Apple Silicon? ✔ OpenRouter offers the 31B model through a free API The real win is not faster chat. It is having Hermes build, retry, check its work, and operate in the background without charging you for every loop.

HERMES CAN NOW RUN FOR FREE FOREVER A new Gemma 4 update just removed the biggest problem with local AI agents. The Upgrade: → Gemma 4 runs around 90% faster on Apple Silicon using Ollama + MLX → Plug it into Hermes with a few terminal commands → Run private agent workflows without subscriptions, token limits, or API bills What It Can Actually Do: ✓ Build and preview apps locally ✓ Use /learn to turn tutorials into permanent skills ✓ Read files, analyse landing pages, summarise emails, and track AI news ✓ Run loops until a task is complete instead of waiting for another prompt ✓ Launch multiple Gemma 4 subagents to work on separate tasks in parallel No Apple Silicon? ✔ OpenRouter offers the 31B model through a free API The real win is not faster chat. It is having Hermes build, retry, check its work, and operate in the background without charging you for every loop.

Julian Goldie SEO

11,363 views • 2 months ago

🚨 Founders: free, private, 100% local AI is finally here I downloaded Qwen 3.6 and ran it on my MacBook inside Strawberry browser. I couldn't believe it. We now have 100% free and private AI that is on par with the best models from OpenAI, Anthropic and Google. (see video!) The CTO of Hugging Face called this "the second revolution of AI." He's right. If you are a building an AI product, you HAVE to start thinking about how you can leverage open source models in your product. It's only a matter of time until local models are mainstream and can run on most people's devices. LLMs are commoditizing. The human brain only requires a AAA battery's worth of energy to run. If biology figured out efficient intelligence, software can too. Maybe we won't need artificial super intelligence and thousands of data centres to do most economically valuable work. Maybe there's a future where AI agents just run on your laptop, fine-tuned to you, fully owned by you, costing only what your energy bill costs. In this future, it's all about building the most delightful, intuitive experience. We've been building for exactly this moment. Stay tuned.

🚨 Founders: free, private, 100% local AI is finally here I downloaded Qwen 3.6 and ran it on my MacBook inside Strawberry browser. I couldn't believe it. We now have 100% free and private AI that is on par with the best models from OpenAI, Anthropic and Google. (see video!) The CTO of Hugging Face called this "the second revolution of AI." He's right. If you are a building an AI product, you HAVE to start thinking about how you can leverage open source models in your product. It's only a matter of time until local models are mainstream and can run on most people's devices. LLMs are commoditizing. The human brain only requires a AAA battery's worth of energy to run. If biology figured out efficient intelligence, software can too. Maybe we won't need artificial super intelligence and thousands of data centres to do most economically valuable work. Maybe there's a future where AI agents just run on your laptop, fine-tuned to you, fully owned by you, costing only what your energy bill costs. In this future, it's all about building the most delightful, intuitive experience. We've been building for exactly this moment. Stay tuned.

Charles Maddock

12,731 views • 4 months ago

🚨 One orchestrator. 10 parallel agents. 100+ tokens a second. All local. The Google Gemma team just dropped a MASSIVE demo for Gemma 4 26B. They built a concurrent workflow that lets the 26B model coordinate an entire team of sub-agents on your machine. Out of the box, the cookbook lets you run 10 parallel agents to: → Code an entire SVG art gallery in seconds → Translate text simultaneously → Generate ASCII art → Write parallel code Spinning up multi-agent systems locally has never looked this fast or this accessible. 100% free and open-source. repo link in 🧵↓

🚨 One orchestrator. 10 parallel agents. 100+ tokens a second. All local. The Google Gemma team just dropped a MASSIVE demo for Gemma 4 26B. They built a concurrent workflow that lets the 26B model coordinate an entire team of sub-agents on your machine. Out of the box, the cookbook lets you run 10 parallel agents to: → Code an entire SVG art gallery in seconds → Translate text simultaneously → Generate ASCII art → Write parallel code Spinning up multi-agent systems locally has never looked this fast or this accessible. 100% free and open-source. repo link in 🧵↓

Charly Wargnier

31,627 views • 2 months ago

IF YOU HAVE BEEN HOLDING OFF ON HERMES AGENT BECAUSE OF API COSTS, READ THIS FIRST. Four real ways to run it for free. Local, through Ollama, complete privacy and no rate limits. Cloud, through free tiers from Groq, OpenRouter, or NVIDIA NIM, no card required. A subscription you already have, GitHub Copilot connects natively. A fallback configuration so a rate limit on one provider does not stop your whole session. Hermes Agent is free and open source. Now there is no excuse on the model side either. Bookmark this. Follow CyrilXBT

IF YOU HAVE BEEN HOLDING OFF ON HERMES AGENT BECAUSE OF API COSTS, READ THIS FIRST. Four real ways to run it for free. Local, through Ollama, complete privacy and no rate limits. Cloud, through free tiers from Groq, OpenRouter, or NVIDIA NIM, no card required. A subscription you already have, GitHub Copilot connects natively. A fallback configuration so a rate limit on one provider does not stop your whole session. Hermes Agent is free and open source. Now there is no excuse on the model side either. Bookmark this. Follow CyrilXBT

CyrilXBT

28,802 views • 2 months ago

INTEL JUST QUIETLY BUILT THE CHEAPEST PATH TO 128GB OF LOCAL AI VRAM, AND IT BEATS NVIDIA'S DGX SPARK BY 2X FOR THE SAME $4,000 00:11 four Arc Pro B70s racked in one chassis. 32GB of GDDR6 each, $949 MSRP, roughly $1,000 street per card stack four and you get 128GB of VRAM for about $4,000 total. a lab benchmarked the quad against a DGX Spark and a single RTX Pro 6000. the four B70s doubled the Spark or better they trail the Pro 6000, but that card is $10,000. so the real choice is now $4K for 128GB from Intel or $10K for 96GB from NVIDIA the article covers the DGX Spark at $3,999 as the single-desk local AI ceiling. this Intel quad matches the price, beats the memory throughput, and nobody is talking about it yet save this before Intel's VRAM-per-dollar advantage becomes the default homelab build ↓

INTEL JUST QUIETLY BUILT THE CHEAPEST PATH TO 128GB OF LOCAL AI VRAM, AND IT BEATS NVIDIA'S DGX SPARK BY 2X FOR THE SAME $4,000 00:11 four Arc Pro B70s racked in one chassis. 32GB of GDDR6 each, $949 MSRP, roughly $1,000 street per card stack four and you get 128GB of VRAM for about $4,000 total. a lab benchmarked the quad against a DGX Spark and a single RTX Pro 6000. the four B70s doubled the Spark or better they trail the Pro 6000, but that card is $10,000. so the real choice is now $4K for 128GB from Intel or $10K for 96GB from NVIDIA the article covers the DGX Spark at $3,999 as the single-desk local AI ceiling. this Intel quad matches the price, beats the memory throughput, and nobody is talking about it yet save this before Intel's VRAM-per-dollar advantage becomes the default homelab build ↓

NO1ennn

139,803 views • 1 month ago