Rapid-MLX serves local models on a Mac through OpenAI-compatible (chat completions, responses) and Anthropic Messages APIs, with a focus on reliable tool calling for coding agents. rapid-mlx launch starts an agent such as Codex, Claude Code, OpenCode, Goose or Crush against a local model.
It uses continuous batching and a prefix cache saved to disk between restarts. The project publishes its speed comparisons against mlx-lm, oMLX and LM Studio with method and raw data on its site.
It needs an Apple silicon Mac on macOS 14 or later; pip installs need Python 3.12+. It's free and open source (Apache 2.0) and runs on your Mac.
How to Get It
brew install rapid-mlxcurl -fsSL https://rapidmlx.com/install.sh | bashuv tool install rapid-mlx@latestOfficial 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
Codex CLICoding
OpenCodeCodingInformation
- Developer
- Rapid-MLX
- Category
- Run models locally
- Price
- Free
- Your data
- Runs on your Mac
- Licence
- Apache-2.0
- Mac
- macOS 14.0 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
oMLXRun locallyRapid-MLX is a product of Rapid-MLX; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.