---
title: "Nativ: Run AI Models Locally on Your Mac"
source: "Simon Willison 博客（Atom）"
source_tier: "t2"
url: "https://simonwillison.net/2026/Jul/21/nativ/#atom-everything"
permalink: "https://feed.astralor.com/items/itm_f9e9285781717688ac6961b1"
published: "2026-07-21T14:22:27.000Z"
score: 75
channel: "ai"
tags: ["macOS","MLX","Nativ","Prince Canuma","Local LLM"]
---

# Nativ: Run AI Models Locally on Your Mac

## AI commentary

> If you own a Mac and want to use LLMs privately and smoothly, Nativ might be the tool you've been waiting for. It brings the experience of local models on par with ChatGPT's desktop app, while being even more developer-friendly. Especially for those already using MLX or Hugging Face models, it offers near-zero configuration.

## At a glance

Nativ is a new project by developer Prince Canuma, built on MLX to provide a full macOS desktop application for running AI models locally. It features a chat interface and a localhost API server, and automatically detects models already cached from Hugging Face, similar to LM Studio but optimized for Apple Silicon. This project extends the author's previous excellent MLX-VLM library, further lowering the barrier to using local LLMs.

## Key points

- Nativ offers a native macOS desktop app with both a chat interface and a local API server.
- Automatically detects models already downloaded in your Hugging Face cache for seamless integration.
- Built on the MLX framework, optimized for Apple Silicon performance.
- Developed by Prince Canuma, creator of the popular MLX-VLM library, with high community anticipation.

## Full text

Nativ: Run AI models locally on your Mac Prince Canuma is the developer behind the excellent MLX-VLM Python library for running vision-LLMs using MLX on a 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 Tags: macos, python, ai, generative-ai, local-llms, llms, mlx, prince-canuma

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_f9e9285781717688ac6961b1