Post

Log inSign up

Post

Log inSign up

Unsloth AI on X: "You can now train and run 500+ models locally with our Unsloth Docker image! 🐳 Use our new GUI or notebooks workflow. No setup required. Works on NVIDIA and AMD. Guide: https://t.co/ER5lOLGQa5 GitHub: https://t.co/aZWYAtakBP"

@UnslothAI
Unsloth AI
@UnslothAI
You can now train and run 500+ models locally with our Unsloth Docker image! 🐳 Use our new GUI or notebooks workflow. No setup required. Works on NVIDIA and AMD. Guide: unsloth.ai/docs/get-start… GitHub: github.com/unslothai/unsl…
@UnslothAI
Unsloth AI
@UnslothAI
Aug 11
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 +
00:00
3:03 PM · Sep 17, 2026·
55.1K
Views
23

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email

Relevant people

Avatar
Unsloth AI@UnslothAIFollow
Run and train models locally with the Unsloth Desktop app. 🦥 https://t.co/2kXqhhvdCD

Trending now

Terms·Privacy·Cookies·Accessibility·US TIDA·Ads Info·© 2026 X Corp.
  • @UnslothAI
    Unsloth AI
    @UnslothAI
    You can now train and run 500+ models locally with our Unsloth Docker image! 🐳 Use our new GUI or notebooks workflow. No setup required. Works on NVIDIA and AMD. Guide: unsloth.ai/docs/get-start… GitHub: github.com/unslothai/unsl…
    @UnslothAI
    Unsloth AI
    @UnslothAI
    Aug 11
    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 +
    00:00
    3:03 PM · Sep 17, 2026·
    55.1K
    Views
    23
  • @ibesh_tech
    Ibesh
    @ibesh_tech
    Sep 17
    the real unlock is packaging, not the model count: if the same workflow works across nvidia and amd without setup archaeology, local ai finally becomes something people can try
  • @EmmyBearAI
    Emmy Bear AI
    @EmmyBearAI
    Sep 17
    How far back on the CUDA architectures does this build go? The last time I was working on P100s, I had to hack at it for a few hours to get a working torch version.
  • @malikatifsaleem
    Atif Saleem
    @malikatifsaleem
    Sep 17
    Is it like Unsloth desktop in a docker container?