Prince Canuma 发布 Nativ,一款基于 MLX 的 macOS 桌面应用,提供聊天界面和本地 API 服务器,用于在 Mac 上本地运行 AI 模型。
Nativ:在你的 Mac 上本地运行 AI 模型:https://blaizzy.github.io/nativ/(来源:https://news.ycombinator.com/item?id=48982681)Prince Canuma 是出色的 MLX-VLM 的开发者:https://github.com/Blaizzy/mlx-vlm,这是一个用于在 Mac 上使用 MLX 运行视觉大语言模型(vision-LLMs)的 Python 库。
我对他的新项目感到非常兴奋,该项目将 MLX 封装在完整的 macOS 桌面应用中。它在界面上类似于 LM Studio,同时提供聊天界面和用于访问模型的本地主机 API 服务器。
该应用识别了我以前尝试过并存在于 Hugging Face 缓存目录中的 MLX 模型,这一点非常贴心。
这是 Simon Willison 于 2026 年 7 月 21 日发布的链接文章:/2026/Jul/21/。
每月赞助我 10 美元,即可获得整理好的本月最重要的大语言模型发展动态电子邮件摘要。
Nativ: Run AI models locally on your Mac:https://blaizzy.github.io/nativ/ (via:https://news.ycombinator.com/item?id=48982681) Prince Canuma is the developer behind the excellent MLX-VLM:https://github.com/Blaizzy/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.
This is a link post by Simon Willison, posted on 21st July 2026:/2026/Jul/21/.
Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.