oMLX serves local language, vision, OCR, embedding and reranker models on a Mac with Apple's MLX. A menu bar app starts and stops the server, and a web dashboard handles model downloads, per-model settings, benchmarks and a built-in chat.
It keeps the KV cache in two tiers, hot blocks in memory and cold blocks on the SSD, so a prompt prefix it has seen before is restored instead of recomputed, even after a restart. It exposes OpenAI- and Anthropic-compatible APIs for coding tools such as Claude Code, and handles concurrent requests with continuous batching.
It needs an Apple silicon Mac on macOS 15.0 or later. The DMG is signed and notarized with in-app updates; Homebrew and source installs need Python 3.11 to 3.13.
oMLX is free and open source (Apache 2.0). Models run on your Mac.
How to Get It
brew tap jundot/omlx https://github.com/jundot/omlx && brew install jundot/omlx/omlxOfficial 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
Claude CodeCoding
OpenCodeCodingInformation
- Developer
- Jun Kim
- Category
- Run models locally
- Price
- Free (Free and open source.)
- Your data
- Runs on your Mac
- Licence
- Apache-2.0
- Mac
- macOS 15.0 or later
- iPhone and iPad
- —
- Needs
- M1 or later
- Facts checked
- 2026-11-03
Sources
You Might Also Like
OllamaRun locally
llama.cppRun locally
LM StudioRun locally
Open WebUIRun locally
AnythingLLMRun locally
Locally AIRun locally
apfelRun locally
exoRun locally
Rapid-MLXRun locallyoMLX is a product of Jun Kim; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.