Install · Apple Silicon

One engine.
Choose your surface.

Run Rapid-MLX as a native Mac app or an OpenAI-compatible local server. Same models, same speed, no account.

Download for Mac Install in Terminal

macOS 14+Apple SiliconApache 2.0228 modelsPrompts and code stay on your MacNo account · No cloud · No billing

Rapid-MLX desktop app model selection screen in light mode

How do you want to work?

same engine · two packages

Desktop app

GUI

Click, pick a model, start chatting. No terminal, no config — signed and notarised for macOS.

Signed and notarized
Model library built in
Local chat + server controls

Get the .dmg

Terminal & server

CLI

An OpenAI-compatible server on localhost — drop-in for Cursor, Claude Code, Aider, and anything that speaks the OpenAI API.

$ curl -fsSL https://rapidmlx.com/install.sh | bash

View all install methods

Before you install

Requirements

Rapid-MLX is built for Apple Silicon. Python is installed automatically when needed.

Chip: Apple SiliconM1 or newer
macOS: 14 (Sonoma) or newer
Python: 3.10+Auto-installed if missing
Disk: Engine is tinyModels download on first serve
Memory: Pick a model sized to your RAMLive picker

Terminal & server

Install once.
Serve anything.

One command. It probes for Python, sets up an isolated environment, and puts rapid-mlx on your PATH — no sudo, nothing to sign up for.

Latest 0.12.18What the command does

Recommended · one-line install

$ curl -fsSL https://rapidmlx.com/install.sh | bash

Homebrew · no tap $ brew install rapid-mlx It's in homebrew/core now — no tap, no trust.

Pin a version $ curl -fsSL https://rapidmlx.com/install.sh | bash -s 0.12.18 Pin a specific version or track the latest pre-release.

What this command does

Probes for Python 3.10+ and installs a self-contained python-build-standalone if it's missing.
Creates an isolated virtualenv at ~/.rapid-mlx — nothing touches your system Python.
Symlinks the rapid-mlx binary into ~/.local/bin.
No sudo. Read the script first at rapidmlx.com/install.sh if you prefer.

Other ways to install: pip · from source

Already manage your own Python 3.10+ environment? Install straight from PyPI:

$ pip install rapid-mlx

Add TTS / STT support with the audio extra, or build from source — the full repo, including the eval framework, is on GitHub:

$ pip install 'rapid-mlx[audio]'

First-request walkthrough

Then — serve a model in one line

Auto-downloads on first run

# auto-downloads on first run $ rapid-mlx serve qwen3.5-4b-4bit serving on http://localhost:8000/v1

That's an OpenAI-compatible endpoint. Point Cursor, Claude Code, Aider, or any OpenAI client at http://localhost:8000/v1 and you're running locally.

Make your first request