LocalAI is one binary with an OpenAI-compatible API in front; it also speaks the Anthropic, Ollama and ElevenLabs APIs. It installs engines such as llama.cpp, MLX, MLX-VLM, whisper.cpp and diffusers as separate backends when a model needs them.
On Apple silicon it uses Metal. Install it with Homebrew; the project's own macOS disk image isn't signed by Apple, and no minimum macOS is stated.
LocalAI is free and open source (MIT) and runs on your own machine.
How to Get It
brew install localaiOfficial downloads only. MLX never re-hosts an app, and never runs a command for you.
MLX Score
Ranked against the run models locally listings, from real public data only. How the score works.
Information
- Developer
- Ettore Di Giacinto (mudler)
- Category
- Run models locally
- Price
- Free
- Your data
- Runs on your Mac
- Licence
- MIT
- Mac
- Runs on a Mac (no minimum stated)
- iPhone and iPad
- —
- Facts checked
- 2026-11-01
Sources
You Might Also Like
OllamaRun locally
llama.cppRun locally
LM StudioRun locally
Open WebUIRun locally
AnythingLLMRun locally
exoRun locally
LlamaRun locally
vMLX (MLX Studio)Run locallyLocalAI is a product of Ettore Di Giacinto (mudler); MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.