AdvertiseWatchSubscribe
Updated , rescanned every two hoursSunday, November 1, 2026

▲ 131 today2.3k starsZig

Apple Silicon gets a native OpenAI-compatible AI server

InferenceLLMsCoding

ddalcu/mlx-serve: preview

What is mlx-serve?

MLX-Serve lets you download and run LLMs locally on Macs without Python, exposing the same OpenAI, Anthropic and Ollama APIs. A Swift front-end app also offers chat, code assistants, image, music, voice and video generation on the device.

Who it is for

Mac developers and privacy-concerned AI users can experiment with powerful models offline, avoiding cloud costs and data exposure.

How to try it

brew install --cask mlx-serve

Get the signal first.

Join the list for the morning email: the day's biggest AI launches, explained in five minutes. Unsubscribe any time.

Prefer a reader? Follow the RSS feed.