• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Unsloth AI Introduces Desktop App for Local Models

    Users can run and train models on Mac, Windows, and Linux hardware.

    PG
    DH
    HT
    9 Sources, 50d ago, first seen 50d ago

    TLDR

    Unsloth AI posted an announcement introducing Unsloth Desktop as the first desktop app to run and train models locally. The open-source release supports MLX, GGUF, diffusion image and video models, and audio. It runs on Mac, Windows, Linux, and WSL. Co-founder Daniel Han stated that users can handle inference, training, remote serving, code execution, and tool calls in one interface. Multiple accounts including Paul Graham shared the post, and the company account confirmed the app works across CPU and multi-GPU setups.

    Combined views

    744.6K

    9 Sources, first seen 50d ago

    Combined views

    744.6K

    9 Sources, first seen 50d ago

    4.9K likes
    4.9K likes
    261 comments
    3.3K saves
    1.5K reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source
    261 comments
    3.3K saves
    1.5K reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    9 Sources

    @UnslothAIIntroducing 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 http://unsloth.ai and GitHub. GitHub: https://github.com/unslothai/unsloth Blog and Guide: https://unsloth.ai/docs/desktop
    @TeksEdgeOh 💩! @UnslothAI now has a desktop app! 🔥 LM Studio just got some serious competition in the Local AI desktop space but that isn't the real news. Unsloth Desktop launched and it goes considerably beyond simply downloading and chatting with local LLMs. 🧠 Run AND train models locally 🖥️ Windows / Linux / Mac 🎮 NVIDIA / AMD / Intel / Apple Silicon / CPU / multi-GPU 📦 GGUF + MLX + image/video diffusion + audio 🤖 Connect Claude Code, Codex, Hermes + OpenClaw to local models 🛠️ Tool calling + sandboxed code execution 🔎 Private search + deep research + RAG + MCP 📤 GGUF / NVFP4 export ⚡ Claims up to 2× faster training with 70% less VRAM 🎯 LM Studio made running local models approachable. Unsloth now wants to do the same thing for the entire Local AI workflow including inference, training, agents and tools from one desktop app. If they execute on this well, the Local AI desktop is becoming a real software category. That final sentence is probably the most interesting strategic angle. The competition isn't merely Unsloth vs LM Studio. We're starting to get competing desktop operating environments for Local AI.
    @danielhanchenUnsloth Desktop is out! ✨ It's the first desktop app that allows you to train and run models You do everything with it, run + train diffusion image/video, serve models remotely, code execution, inference and more! It works on nearly all hardware and Mac, Windows, Linux and WSL. Would love for you all to try it out and let us know what you think of it! 🥰 Try it on GitHub: https://github.com/unslothai/unsloth
    @MohapatraHemantYou can now be a sloth because Unsloth is coming to your desktop! 🦥🦥
    @paulgRT @UnslothAI: Introducing Unsloth Desktop 🦥 The first desktop app to run and train models locally. • Open-source. Runs on Mac, Windows an…
    @harjtaggarRT @UnslothAI: Introducing Unsloth Desktop 🦥 The first desktop app to run and train models locally. • Open-source. Runs on Mac, Windows an…

    9 Sources

    @UnslothAIIntroducing 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 http://unsloth.ai and GitHub. GitHub: https://github.com/unslothai/unsloth Blog and Guide: https://unsloth.ai/docs/desktop
    @TeksEdgeOh 💩! @UnslothAI now has a desktop app! 🔥 LM Studio just got some serious competition in the Local AI desktop space but that isn't the real news. Unsloth Desktop launched and it goes considerably beyond simply downloading and chatting with local LLMs. 🧠 Run AND train models locally 🖥️ Windows / Linux / Mac 🎮 NVIDIA / AMD / Intel / Apple Silicon / CPU / multi-GPU 📦 GGUF + MLX + image/video diffusion + audio 🤖 Connect Claude Code, Codex, Hermes + OpenClaw to local models 🛠️ Tool calling + sandboxed code execution 🔎 Private search + deep research + RAG + MCP 📤 GGUF / NVFP4 export ⚡ Claims up to 2× faster training with 70% less VRAM 🎯 LM Studio made running local models approachable. Unsloth now wants to do the same thing for the entire Local AI workflow including inference, training, agents and tools from one desktop app. If they execute on this well, the Local AI desktop is becoming a real software category. That final sentence is probably the most interesting strategic angle. The competition isn't merely Unsloth vs LM Studio. We're starting to get competing desktop operating environments for Local AI.
    @danielhanchenUnsloth Desktop is out! ✨ It's the first desktop app that allows you to train and run models You do everything with it, run + train diffusion image/video, serve models remotely, code execution, inference and more! It works on nearly all hardware and Mac, Windows, Linux and WSL. Would love for you all to try it out and let us know what you think of it! 🥰 Try it on GitHub: https://github.com/unslothai/unsloth
    @MohapatraHemantYou can now be a sloth because Unsloth is coming to your desktop! 🦥🦥
    @paulgRT @UnslothAI: Introducing Unsloth Desktop 🦥 The first desktop app to run and train models locally. • Open-source. Runs on Mac, Windows an…
    @harjtaggarRT @UnslothAI: Introducing Unsloth Desktop 🦥 The first desktop app to run and train models locally. • Open-source. Runs on Mac, Windows an…