Pico MLX Server - run the fastest LLM models locally on your Mac

Learn how to set up Pico MLX Server to run MLX‑optimized LLMs locally on Apple Silicon, using an OpenAI‑compatible API without terminal commands.

Overview

Pico MLX Server is an open source tool to run MLX-optimized LLM models on Mac. MLX is Apple’s new AI framework, specifically optimized for Apple Silicon. Pico MLX Server provides an OpenAI-compatible API for seamless integration with existing AI chat apps. Just set any app’s endpoint to localhost and it works.

Accessible from the menu bar, Pico MLX Server offers a straightforward interface for managing server operations. No terminal commands necessary.

Pico MLX Server is a part of a collection of open-source, Swift-based AI tools designed for iOS and macOS developers.

Links

https://github.com/ronaldmannak/PicoMLXServer/issues
PicoMLXServer: Issues with lightweight MLX server for AI models.

Tech stack