What it does
Vision language models are AI models that can look at pictures and talk about them. MLX-VLM runs these on Apple Mac computers using MLX, Apple's toolkit for machine learning.
It supports many models, including ones for reading text in documents (OCR). You can use it from the command line, a simple chat window, Python code or a local server.
It can also fine-tune models, teaching them new skills with your own examples.
Who it's for
Mac users and developers who want to run image-understanding AI privately on their own machine.
Can I use it without coding?
With some setup. Installed as a Python package; an optional chat window is available after install. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Mac
- 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
- Install Python on your Mac, then install MLX-VLM with Python's package installer, including the optional chat window extra.
- Start the chat window and pick a model to try with your own images.
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 (MIT): Very permissive: free to use, change and share, including for business.
- More on staying safe