Llama sits in the menu bar and runs a local server at localhost:9931. It recommends models your Mac can run, installs any GGUF model from Hugging Face in one click, and sets each one up for your Mac. Models load when asked for and unload when idle.
It's built on llama.cpp by the GGML organisation and shares its model cache. Homebrew lists it for Apple silicon Macs on macOS 15 or later.
Llama is free and open source (MIT). Models run on your Mac and no data leaves it.
How to Get It
brew install --cask llama-appOfficial 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.
Pairs Well With
llama.cppRun locallyInformation
- Developer
- ggml-org
- Category
- Run models locally
- Price
- Free
- Your data
- Runs on your Mac
- Licence
- MIT
- Mac
- macOS 15.0 or later
- iPhone and iPad
- —
- Needs
- M1 or later
- Facts checked
- 2026-11-01
Sources
You Might Also Like
OllamaRun locally
LM StudioRun locally
Open WebUIRun locally
AnythingLLMRun locally
exoRun locally
vMLX (MLX Studio)Run locallyLlama is a product of ggml-org; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.