Nativ: Run AI models locally on your Mac I'm really excited about his new project, which wraps MLX in a full macOS desktop application. It's similar in shape to LM Studio, providing both a chat interface and a localhost API server for accessing models.
The app picked up MLX models I had already tried that were present in my Hugging Face cache directory, which was a nice touch.
Via [Hacker News](https://news.ycombinator.com/item?id=48982681)
Tags: [macos](https://simonwillison.net/tags/macos), [python](https://simonwillison.net/tags/python), [ai](https://simonwillison.net/tags/ai), [generative-ai](https://simonwillison.net/tags/generative-ai), [local-llms](https://simonwillison.net/tags/local-llms), [llms](https://simonwillison.net/tags/llms), [mlx](https://simonwillison.net/tags/mlx), [prince-canuma](https://simonwillison.net/tags/prince-canuma)
source & further reading
simonwillison.net — original article
A Fireside Chat with Cat and Thariq from the Claude Code team
Reverse-engineering is cheap now
Who’s Afraid of Chinese Models?