LLM runs prompts and chats from the terminal or Python against many models: OpenAI, Anthropic's Claude and Google's Gemini through plugins, any OpenAI-compatible endpoint such as LM Studio, and models on your own device through plugins.
Install it with Homebrew, uv or pip (Python 3.10 or newer).
It's free and open source (Apache 2.0). Prompts go to whichever model you choose: a cloud API, or a model running on your Mac.
Official 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.
LLM is a product of Simon Willison; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.