LM Studio searches Hugging Face for models, downloads them and runs them on your Mac. It has an MLX engine for Apple silicon next to llama.cpp, so MLX and GGUF models can run side by side, and a local server that other apps can call. The `lms` command line tool ships with the app.
It needs an Apple silicon Mac (M1 or later) and macOS 14.0 or newer. LM Studio recommends 16 GB of memory or more; 8 GB Macs work with smaller models. Intel Macs aren't supported.
LM Studio is free to use at home and at work. Models run on your Mac and it can work fully offline once the models are downloaded. The desktop app's source code isn't published; its command line tool is MIT-licensed.
How to Get It
brew install --cask lm-studioOfficial 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
- Element Labs
- Category
- Run models locally
- Price
- Free (Free at home and at work; an Enterprise plan is offered for companies.)
- Your data
- Runs on your Mac
- Licence
- Proprietary
- Mac
- macOS 14.0 or later
- iPhone and iPad
- —
- Needs
- M1 or later
- Facts checked
- 2026-11-01
Sources
Compare
You Might Also Like
OllamaRun locally
Open WebUIRun locally
AnythingLLMRun locally
exoRun locally
LlamaRun locally
vMLX (MLX Studio)Run locallyLM Studio is a product of Element Labs; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.