mlx-serve

![MLX-Serve, a local LLM and media server for Apple Silicon](website/assets/mlx-serve-header.jpg)

# MLX-Serve

Run open models on your Mac: chat, coding agents, images, video, music, speech and 3D. One native app and one local server that speaks the OpenAI, Anthropic and Ollama APIs. It runs offline, needs no Python and no account, and it's MIT licensed.

[![Release](https://img.shields.io/github/v/release/ddalcu/mlx-serve?style=flat-square&color=0071e3)](https://github.com/ddalcu/mlx-serve/releases/latest)
[![Downloads](https://img.shields.io/github/downloads/ddalcu/mlx-serve/total?style=flat-square&color=30d158)](https://github.com/ddalcu/mlx-serve/releases)
[![Stars](https://img.shields.io/github/stars/ddalcu/mlx-serve?style=flat-square&color=f7a41d)](https://github.com/ddalcu/mlx-serve/stargazers)
[![License: MIT](https://img.shields.io/badge/license-MIT-blue?style=flat-square)](LICENSE)

**[Download for Mac](https://github.com/ddalcu/mlx-serve/releases/latest/download/MLX-Serve.dmg)** · [Homebrew](#install) · [iPhone](https://apps.apple.com/us/app/mlx-chat-local-ai/id6787603518) · [Linux](#linux-and-windows) · [mlxserve.com](https://mlxserve.com/) · [简体中文](README.zh-CN.md)

![Chatting with a local model, making a picture and coding with Claude Code, all on one Mac](website/assets/demo.gif)

## Install

**The app.** [Download MLX-Serve](https://github.com/ddalcu/mlx-serve/releases/latest/download/MLX-Serve.dmg), drag it to Applications and open it. It needs macOS 26.2 or later on Apple Silicon, suggests a model that fits your Mac, and updates itself.

**Homebrew.**

```bash
brew tap ddalcu/mlx-serve https://github.com/ddalcu/mlx-serve
brew trust ddalcu/mlx-serve
brew install --cask mlx-serve   # the app
brew install mlx-serve          # or only the command-line server
```

**The terminal**, if you know Ollama:

```bash
mlx-serve run gemma4          # downloads Gemma 4 E4B, serves it and chats right here
mlx-serve pull gemma4:26b     # download only, resumable
mlx-serve serve               # serve everything you downloaded; models load when asked for
```

The server listens on `http://localhost:11234`. Point any OpenAI, Anthropic or Ollama client at it, or open that address in a browser for the built-in web console.

### iPhone

[MLX-Serve](https://apps.apple.com/us/app/mlx-chat-local-ai/id6787603518) puts the same engine on your iPhone: chat with Gemma 4, clone your voice, and make pictures and music, all on the phone and offline. It needs an A17 Pro-class iPhone or newer with iOS 26.

### Linux and Windows

Every release has Linux downloads for NVIDIA GPUs: x64 for RTX 20 to 50 cards, arm64 for DGX Spark, GH200 and Jetson Thor. On Windows with an NVIDIA card, one script builds it. Details are in [docs/building.md](docs/building.md#linux-and-windows-nvidia).

## What it does

- **Coding agents on a local model.** `mlx-serve launch claude` starts Claude Code against your Mac, set up with the model's real context window. Codex, OpenCode, pi, G