MLX-VLM runs vision language models, which read images as well as text, and omni models with audio and video, using Apple's MLX. It has a command line, a Python API, an optional Gradio chat UI and an OpenAI-style server, and it can fine-tune models.
It's a Python package for Apple silicon Macs and needs MLX, which runs on macOS 14.0 or later.
It's free and open source (MIT) and runs on your Mac.
pip install -U mlx-vlmOfficial downloads only. MLX never re-hosts an app, and never runs a command for you.
Ranked against the developer tools listings, from real public data only. How the score works.
MLX-VLM is a product of Prince Canuma; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.