What it does
Unsloth is a desktop app for Windows, Mac and Linux that runs open AI models on your own computer, including chat, image, audio and video models. You can chat with them, connect them to coding tools like Claude Code, search the web, and reach your models from other devices on your home network.
Its main strength is fine-tuning: teaching an existing model new skills using your own examples. Its makers say it trains models about twice as fast while using much less graphics-card memory, without losing accuracy. It can also build training data from PDFs, spreadsheets and Word files, and export finished models in common formats.
Besides the desktop app, there is a web interface and a Python library for programmers.
Who it's for
Hobbyists and developers who want to run AI privately or adapt models to their own tasks.
Can I use it without coding?
Yes. There is a downloadable desktop app. Training models needs a capable computer, ideally with a good graphics card. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Windows, Linux, Mac, Web browser
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Not needed
Try it
- Download Unsloth Desktop for your computer from the Unsloth website or GitHub releases.
- Open the app to run AI models on your own computer.
- Train a model on your own data, built from files such as PDFs or spreadsheets.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page or the official download page above. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuningHacker News · Dec 2023
- Unsloth: 80% faster, 50% less memory, 0% accuracy loss Llama finetuningHacker News · Dec 2023