Skip to content
mlx.app

MLX Omni Server

An OpenAI-compatible server that's actually running MLX underneath.

When to use it

Use this when you already have OpenAI-SDK client code and want it hitting MLX-native chat, image and speech endpoints on your Mac.

Alternatives in Servers

Ollama

The `ollama run` command that made local models a one-liner.

LM Studio MLX Engine

LM Studio's own MLX backend, open-sourced separately from the app.

Open WebUI

A ChatGPT-shaped front end you point at any local backend.

exo

Turns a pile of Macs (and phones) into one inference cluster.