What it does
Transformer Lab is an open-source workspace for working with AI models. You can download popular open models, chat with them, fine-tune them on your own data and measure how well they perform. It also supports image generation and text-to-speech models.
The individual edition runs on one computer, and the README says no data leaves your machine. A teams edition sends training jobs to GPU clusters or cloud providers. You use it through a web interface in your browser.
Who it's for
Researchers and hobbyists who want to train and experiment with AI models without stitching many tools together.
Can I use it without coding?
With some setup. You run an install script, start it and open it in your browser; it needs an Apple Silicon Mac or a computer with a suitable graphics card. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Mac, Linux, Windows, Server
- Computer
- Works best on a powerful computer or one with a graphics card (GPU)
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
- Check that you have an Apple Silicon Mac, or a Linux or Windows computer with a suitable graphics card.
- Run the install script from the README, then start Transformer Lab.
- Open it in your web browser and download a model to try.
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. Copies with similar names exist for many popular projects.
- License (AGPL-3.0): Free to use; if you run a changed version as an online service, you must share your source code.
- More on staying safe
Where people are talking about it
- Show HN: Open-Source Alternative to OpenAI Platform, for Local ModelsHacker News · Jan 2025