What it does
oMLX lets you run large language models on a Mac with an Apple Silicon chip (M1 or newer). You manage it from the menu bar: pick which models stay loaded, swap in heavier ones when needed and set limits.
It keeps a cache of past conversation context in memory and on the SSD drive, which its makers say makes local models practical for longer work such as coding with tools like Claude Code. Other apps can connect to it as if it were the OpenAI service, and it also has a built-in chat page.
Who it's for
Mac owners who want to run AI models privately on their own machine.
Can I use it without coding?
Yes. There is a downloadable Mac app with a setup screen; it needs a recent macOS and an Apple Silicon Mac. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Mac
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
- Download the Mac app from the project's releases page and drag it to Applications.
- Open oMLX and follow the Welcome screen to choose a model folder and start the server.
- Download your first model and chat with it in the built-in chat.
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