正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Introducing Atomic Local AI Server ⚡ Choose inference engine. Run local models. Connect your agents. • Multiple engines: llama.cpp, vLLM, SGLang, TensorRT, MLX, Prism and more. • Local AI server with an OpenAI-compatible API. • One-command engine installation matched to your GPU, CPU or NPU. • Pull from 3M... Hugging Face models in GGUF, MLX or safetensors formats. • Run on Windows, Linux, Apple Silicon and NVIDIA hardware, including RTX, Blackwell and DGX Spark. AMD Ryzen Halo support coming soon. • Connect Hermes, OpenClaw, Claude, Codex, Pi agent and others. • Generate images and videos with stable-diffusion. • Manage everything through CLI or web UI. • Remote access via Cloudflare tunnels Free. Open source. Local. 👇show more

atomic.chat

20,176 subscribers

40,325 次观看 • 1 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

21 条评论

Konstantin Gladych 的头像

Konstantin Gladych1 天前

Nice CLI. All engines in one place!

Schwarzer Ritter 的头像

Schwarzer Ritter1 天前

Most versatile tool for your inference factory imo

Ivan Fioravanti 的头像

Ivan Fioravanti1 天前

Mega release! Nearly any inference engine is supported now!

Alex Tatu 的头像

Alex Tatu1 天前

One-command engine install matched to my hardware, congrats 🔥

Valerii Brizhatiuk 的头像

Valerii Brizhatiuk1 天前

I love the cli

Aether 的头像

Aether1 天前

🔥🔥 when is strata coming?

atomic.chat 的头像

atomic.chat1 天前

working on it, stay tuned)

out 的头像

out1 天前

Nice, can we have a gui though? TUI's are annoying to use

꧁🐬 ⭑⭒ 🐬 ⭑⭒ 🐬꧂ 的头像

꧁🐬 ⭑⭒ 🐬 ⭑⭒ 🐬꧂1 天前

Is this different than Atomic Chat? is there an app in the Apple store? Confused. You video runs too fast🥵

三分钟懂行的头像

三分钟懂行1 天前

按硬件匹配引擎这一步挺吸引人。本地跑模型，能少花点时间处理安装和兼容，才更容易真的用起来。

Mohammad Vazin 的头像

Mohammad Vazin1 天前

An OpenAI-compatible endpoint on the LAN is an open door if it binds to 0.0.0.0 without a key. Does it listen on localhost only by default, or require an API key for remote clients?

Deduped 的头像

Deduped1 天前

For multi-engine setups the cleanest guardrail is a one-line wrapper: set ATOMIC_ENGINE=llama.cpp before the serve call so every request pins the same backend and you never get silent answer drift between llama.cpp and vLLM.

Yuri Moreno 的头像

Yuri Moreno1 天前

How does it differ from LM Studio?

Raz Bhimani 的头像

Raz Bhimani1 天前

switching engines on the same model is where i'd worry. llama.cpp and vLLM can give slightly different answers, so logging which engine ran each call would save a lot of debugging.

安叫兽|Bird🕊️ 🔶 BNB 的头像

安叫兽|Bird🕊️ 🔶 BNB1 天前

能随时切换推理引擎挺实用，关键看切过去后 Agent 的工具调用稳不稳。

Peasant Smith 的头像

Peasant Smith1 天前

You know what, that is clever!

ルナ🌙 AIクオンツ美少女【FIS】的头像

ルナ🌙 AIクオンツ美少女【FIS】1 天前

Engine soup? Without q8_0 KV-cache, you’re just leaking VRAM. We cut footprint 43% on dual GPUs.

ApexAiTech 的头像

ApexAiTech1 天前

Run local models free

Velgberg 的头像

Velgberg1 天前

Letting people swap between llama.cpp, vLLM and MLX behind one OpenAI compatible API is handy for comparing real throughput on their own hardware. Does it keep the same model files across engines or does each one need its own format?

atomic.chat 的头像

atomic.chat1 天前

you will generally need different model files for each engine. you can compare the same model across engines, but each needs a compatible format

Volink 的头像

Volink1 天前

llama.cpp, vLLM, SGLang, TensorRT and MLX behind one OpenAI-compatible endpoint is more than I expected from a local server.

相关视频

Atomic Chat now runs on NVIDIA RTX Spark 💻 Generate text, images and videos with open models. Power your agents via a local API server. All on your own hardware. Explore RTX Spark:

Atomic Chat now runs on NVIDIA RTX Spark 💻 Generate text, images and videos with open models. Power your agents via a local API server. All on your own hardware. Explore RTX Spark:

atomic.chat

14,241 次观看 • 21 天前

Introducing Unsloth Desktop 🦥 The first desktop app to run and train models locally. • Open-source. Runs on Mac, Windows and Linux • Supports MLX, diffusion image/video, audio, GGUF • Connect Claude Code and Codex to local LLMs • 50% more accurate, self-healing tool calls + sandboxed code exec • Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac • Train models 2× faster with 70% less VRAM • Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF) • Use Unsloth’s OpenAI-compatible API and cloud models • Securely deploy LLMs remotely and access anywhere Unsloth Desktop is now available on and GitHub. GitHub: Blog and Guide:

Introducing Unsloth Desktop 🦥 The first desktop app to run and train models locally. • Open-source. Runs on Mac, Windows and Linux • Supports MLX, diffusion image/video, audio, GGUF • Connect Claude Code and Codex to local LLMs • 50% more accurate, self-healing tool calls + sandboxed code exec • Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac • Train models 2× faster with 70% less VRAM • Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF) • Use Unsloth’s OpenAI-compatible API and cloud models • Securely deploy LLMs remotely and access anywhere Unsloth Desktop is now available on and GitHub. GitHub: Blog and Guide:

Unsloth AI

888,317 次观看 • 2 个月前

Which models can your machine actually run? Magnitude is a 100% free, open source desktop app that: - profiles your hardware and runs sample calculations - predicts tok/s for every model before you download - recommends the best models, from fast to smart Pick your models and it handles the rest: - downloads and tunes the models for your hardware - connects agents like pi, opencode, hermes in one click - runs models on demand as your agent works Works on whatever hardware you already own: MacBook (Intel or Apple Silicon), Mac Mini, Mac Studio, DGX Spark, Strix Halo, any NVIDIA/AMD GPU, or just a CPU Download it on macOS, Windows, or Linux: Open source:

Which models can your machine actually run? Magnitude is a 100% free, open source desktop app that: - profiles your hardware and runs sample calculations - predicts tok/s for every model before you download - recommends the best models, from fast to smart Pick your models and it handles the rest: - downloads and tunes the models for your hardware - connects agents like pi, opencode, hermes in one click - runs models on demand as your agent works Works on whatever hardware you already own: MacBook (Intel or Apple Silicon), Mac Mini, Mac Studio, DGX Spark, Strix Halo, any NVIDIA/AMD GPU, or just a CPU Download it on macOS, Windows, or Linux: Open source:

Tom Greenwald

50,178 次观看 • 1 个月前

Private AI browser with the OpenClaw agent on free local models Run your agent on Qwen, Gemma, or Nemotron directly in the browser Open source. Private. Runs on your local device

Private AI browser with the OpenClaw agent on free local models Run your agent on Qwen, Gemma, or Nemotron directly in the browser Open source. Private. Runs on your local device

Sigma Browser

115,995 次观看 • 6 个月前

AI at Meta's Muse Glimmer (30B dense, open-weights) launches with SGLang day-0 support. We got ~230 tok/s on a single RTX 5090, with NVFP4 + DFlash on. It also works out of the box on NVIDIA AI Developer RTX Pro 6000, DGX Spark, and MLX for Mac. Speed and reliability have always been the blockers for a local agent. SGLang and Muse Glimmer make a local agent that's blazing fast, always on, and gets things done. Go build and run a local agent on your own machine!🚀

AI at Meta's Muse Glimmer (30B dense, open-weights) launches with SGLang day-0 support. We got ~230 tok/s on a single RTX 5090, with NVFP4 + DFlash on. It also works out of the box on NVIDIA AI Developer RTX Pro 6000, DGX Spark, and MLX for Mac. Speed and reliability have always been the blockers for a local agent. SGLang and Muse Glimmer make a local agent that's blazing fast, always on, and gets things done. Go build and run a local agent on your own machine!🚀

LMSYS Org

44,226 次观看 • 2 个月前

Introducing Magnitude: your actually local agent 100% private and offline. No token costs, no API keys. Open source. Today's agents are local. The model isn't. Every prompt, every file, every secret gets sent straight to Anthropic and OpenAI. Magnitude is built around local models and runs the whole stack itself. The inference engine is part of the agent, so the models run inside it, right on your computer. It lives in your terminal, and setup is one command. Magnitude profiles your hardware and shows you which models fit, with the trade-offs between quality, speed, and memory. Pick one and start working. No painful config or server to babysit. Out of the box, it can use your shell, edit files, and run scripts. Add skills and it can work with Excel, PowerPoint, PDFs or Chrome. Use it for everyday work: - Analyze sensitive data - Manage private notes - Review code and logs - Search and organize files - Build docs or slides npm i -g @magnitudedev/cli GitHub:

Introducing Magnitude: your actually local agent 100% private and offline. No token costs, no API keys. Open source. Today's agents are local. The model isn't. Every prompt, every file, every secret gets sent straight to Anthropic and OpenAI. Magnitude is built around local models and runs the whole stack itself. The inference engine is part of the agent, so the models run inside it, right on your computer. It lives in your terminal, and setup is one command. Magnitude profiles your hardware and shows you which models fit, with the trade-offs between quality, speed, and memory. Pick one and start working. No painful config or server to babysit. Out of the box, it can use your shell, edit files, and run scripts. Add skills and it can work with Excel, PowerPoint, PDFs or Chrome. Use it for everyday work: - Analyze sensitive data - Manage private notes - Review code and logs - Search and organize files - Build docs or slides npm i -g @magnitudedev/cli GitHub:

Tom Greenwald

398,275 次观看 • 3 个月前

Run Cline on Local AI models with Atomic Chat! Cline is a coding agent trusted by 8M+ developers. Write, refactor, ship code securely on your own hardware with local models powered by atomic.chat — no cloud, private, free and open-source

Run Cline on Local AI models with Atomic Chat! Cline is a coding agent trusted by 8M+ developers. Write, refactor, ship code securely on your own hardware with local models powered by atomic.chat — no cloud, private, free and open-source

atomic.chat

44,433 次观看 • 4 个月前

🚨 Abacus AI SuperComputer - Build, Host and Run Any Cloud Service! - 24/7 cloud computer - spin up local LLMs, agents and databases - access 100+ AI models - use Claude, Codex or AntiGravity - run OpenClaw or Hermes - host servers, APIs or run scheduled tasks - prompt -> one cloud service Build, Host and Deploy Anything

🚨 Abacus AI SuperComputer - Build, Host and Run Any Cloud Service! - 24/7 cloud computer - spin up local LLMs, agents and databases - access 100+ AI models - use Claude, Codex or AntiGravity - run OpenClaw or Hermes - host servers, APIs or run scheduled tasks - prompt -> one cloud service Build, Host and Deploy Anything

Abacus.AI

10,526,245 次观看 • 5 个月前

Atomic Chat is now on Hugging Face 🤗 We're officially a Local App on the world's biggest AI hub. Run 200,000+ open-weight models from Hugging Face directly on your device - private, local, and open source!

Atomic Chat is now on Hugging Face 🤗 We're officially a Local App on the world's biggest AI hub. Run 200,000+ open-weight models from Hugging Face directly on your device - private, local, and open source!

atomic.chat

29,420 次观看 • 4 个月前

I switched my Hermes agent to 100% free local models with Magnitude It’s running Qwen 3.6 35B-A3B at ~60 tok/s on my DGX Spark. It’s free, private, and always on running background tasks Hermes set Magnitude up itself. With the CLI it: - Profiled my hardware and found the best models for it - Walked me through the options and let me decide - Switched itself over From there, models load just in time as the agent works and unload when idle Works with Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My Pi, and Cline Copy this prompt and send it to your agent: “Set up local models for me with the Magnitude CLI. Install it with `npm i -g @magnitudedev/cli` (or my package manager), then run `magnitude docs onboarding` and follow the instructions” GitHub:

I switched my Hermes agent to 100% free local models with Magnitude It’s running Qwen 3.6 35B-A3B at ~60 tok/s on my DGX Spark. It’s free, private, and always on running background tasks Hermes set Magnitude up itself. With the CLI it: - Profiled my hardware and found the best models for it - Walked me through the options and let me decide - Switched itself over From there, models load just in time as the agent works and unload when idle Works with Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My Pi, and Cline Copy this prompt and send it to your agent: “Set up local models for me with the Magnitude CLI. Install it with `npm i -g @magnitudedev/cli` (or my package manager), then run `magnitude docs onboarding` and follow the instructions” GitHub:

Tom Greenwald

22,752 次观看 • 2 个月前

Hermes Agent by Nous Research (100k+ ⭐) now inside Atomic Bot: – Free Local models: Qwen, Gemma or – Use your API keys for any provider – Dashboard, terminal, logs and files explorer – Private and Open Source Download MacOS app or run in Cloud👇

Hermes Agent by Nous Research (100k+ ⭐) now inside Atomic Bot: – Free Local models: Qwen, Gemma or – Use your API keys for any provider – Dashboard, terminal, logs and files explorer – Private and Open Source Download MacOS app or run in Cloud👇

atomicbot.ai

345,530 次观看 • 6 个月前

Meet Atomic Agent Desktop! ✦ Local AI-first agent for Mac, Windows & Linux ✦ 4x bigger context window on local models with TurboQuant ✦ Atomic Fusion orchestrates cloud and local models to reduce costs Download Free & Private Agent →

Meet Atomic Agent Desktop! ✦ Local AI-first agent for Mac, Windows & Linux ✦ 4x bigger context window on local models with TurboQuant ✦ Atomic Fusion orchestrates cloud and local models to reduce costs Download Free & Private Agent →

Atomic Agent

90,439 次观看 • 28 天前

Meet June: your private AI agent now with local models on your Mac. Turn the wifi off: Agent, dictation, meeting notes, and your files all in one workspace. 100% free to use with local inference. Open Source. MIT. Local first. Try it:

Meet June: your private AI agent now with local models on your Mac. Turn the wifi off: Agent, dictation, meeting notes, and your files all in one workspace. 100% free to use with local inference. Open Source. MIT. Local first. Try it:

OpenSoftware

17,471 次观看 • 4 个月前

BREAKING $AMD is ready to ship Ryzen AI Halo 🆕 in June 2026!!!! 🚀🚀🚀 AKA Personal/Local AI system. Ryzen AI Max+ 395 (Strix Halo APU) with 128 GB of unified LPDDR5X memory, 40 RDNA 3.5 GPU compute units, and a full ROCm software stack preloaded for both Windows and Linux. AMD Halo is $2,000-$3,000 vs $NVDA Spark $4,699 The main purpose of the AMD Ryzen AI Halo is to serve as a compact, developer focused workstation for running intensive AI workloads locally, specifically building, testing, prototyping, fine-tuning, and deploying generative AI models (like LLMs) and Agentic AI applications without relying on the cloud. Run models with up to 200 billion parameters on your desk using 128 GB of unified memory (shared across CPU, GPU, and NPU). This eliminates cloud costs, latency, data privacy concerns, and internet dependency. ~This is for AI developers, researchers, engineers, and creators. ~Teams or individuals wanting faster iteration, data privacy, and cost savings compared to cloud APIs. ~Users experimenting with open-source models, fine-tuning, inference, and production-like local deployment Source: AMD CES 2026

BREAKING $AMD is ready to ship Ryzen AI Halo 🆕 in June 2026!!!! 🚀🚀🚀 AKA Personal/Local AI system. Ryzen AI Max+ 395 (Strix Halo APU) with 128 GB of unified LPDDR5X memory, 40 RDNA 3.5 GPU compute units, and a full ROCm software stack preloaded for both Windows and Linux. AMD Halo is $2,000-$3,000 vs $NVDA Spark $4,699 The main purpose of the AMD Ryzen AI Halo is to serve as a compact, developer focused workstation for running intensive AI workloads locally, specifically building, testing, prototyping, fine-tuning, and deploying generative AI models (like LLMs) and Agentic AI applications without relying on the cloud. Run models with up to 200 billion parameters on your desk using 128 GB of unified memory (shared across CPU, GPU, and NPU). This eliminates cloud costs, latency, data privacy concerns, and internet dependency. ~This is for AI developers, researchers, engineers, and creators. ~Teams or individuals wanting faster iteration, data privacy, and cost savings compared to cloud APIs. ~Users experimenting with open-source models, fine-tuning, inference, and production-like local deployment Source: AMD CES 2026

Mike

16,121 次观看 • 5 个月前

Build a fully local AI coding agent on Ubuntu using Canonical Workshop and the Qwen3-Coder Inference Snap. In this step-by-step demo, you'll set up an isolated development environment, connect your coding agent to a locally hosted LLM, and run coding tasks without an internet connection. Follow along to recreate the setup on your own machine, using CPU or GPU inference: #Ubuntu #Linux #AI #Agents #Workshop #OpenSource

Build a fully local AI coding agent on Ubuntu using Canonical Workshop and the Qwen3-Coder Inference Snap. In this step-by-step demo, you'll set up an isolated development environment, connect your coding agent to a locally hosted LLM, and run coding tasks without an internet connection. Follow along to recreate the setup on your own machine, using CPU or GPU inference: #Ubuntu #Linux #AI #Agents #Workshop #OpenSource

Ubuntu

42,099 次观看 • 6 天前

It's been an amazing week for open models running on NVIDIA Local AI systems! 👀 Here's a few you’ll want to know about, all ready to run locally on NVIDIA RTX, DGX Spark, DGX Station, and Jetson.

It's been an amazing week for open models running on NVIDIA Local AI systems! 👀 Here's a few you’ll want to know about, all ready to run locally on NVIDIA RTX, DGX Spark, DGX Station, and Jetson.

NVIDIA RTX Spark

60,853 次观看 • 2 个月前

🐆 Rapid-MLX v0.12 is here. We’ve officially evolved from a simple chat app into a full-fledged, on-device AI studio for Apple Silicon! 🖥️✨ We didn't just push the MLX inference engine to its limits and expand support for a massive lineup of local open-source models—we are alpha-launching the highly anticipated Desktop Version. (A huge shoutout to the IoTeX community for grinding through the closed beta with us. Your feedback was incredible and helped shape this beast.) Here are the game-changing features you can run on your Mac right now, 100% free and 100% offline 👇 🚀 Blazing Fast Local LLMs Run anything from 4B up to Qwen3.5-122B completely offline. No guessing games—we recommend models matched perfectly to your Mac's actual RAM. Rich chat includes syntax highlighting, markdown tables, and honest tok/s metrics. 🎨 Local Image Generation A brand new Images tab to render directly on your machine. Pick a model (FLUX.2-klein, Z-Image-Turbo), prompt, and refine. Everything lands in a visual filmstrip. 👁️ Vision & Live Web Tools Attach an image and chat about it with local vision. Need real-time data? Our built-in web tools (weather, search, page-fetch) run mid-answer with strict, transparent privacy controls. 🤖 Plug-and-Play Coding Agents Wire up Claude Code, Codex, Cline, or Continue in seconds. One copy-paste from the Launch tab spins up a local OpenAI/Anthropic-compatible endpoint. 🔒 Private by Design Everything runs on-device. Signed, notarized, and entirely local. Your data stays yours. Turn your Mac into an AI powerhouse today. ⚡️

raullen

34,196 次观看 • 2 个月前

Portable Computer for Windows is now available on AMD Ryzen AI Max Series processors. It makes it easy to run local AI agents that work with your connected apps and local files. Kick off tasks or schedule recurring work that runs entirely on your device.

Portable Computer for Windows is now available on AMD Ryzen AI Max Series processors. It makes it easy to run local AI agents that work with your connected apps and local files. Kick off tasks or schedule recurring work that runs entirely on your device.

Perplexity

77,902 次观看 • 1 个月前

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

41,369 次观看 • 7 个月前

Run KiloCode on open models powered by Atomic Chat Kilo is trusted by 3M+ developers. Code, debug, and build entirely on your device — no cloud, fully private, free and open-source with atomic.chat local AI provider

Run KiloCode on open models powered by Atomic Chat Kilo is trusted by 3M+ developers. Code, debug, and build entirely on your device — no cloud, fully private, free and open-source with atomic.chat local AI provider

atomic.chat

11,990 次观看 • 4 个月前