Federico Viticci(@viticci):The latest oMLX release by @jundotkim is terrific. Finally can use a local model (qwen3.8-flash-next-q4) running on my M3 Ultra Mac Studio, from my iPhone (with Open Minis) to do "real" assistant work. Running at a respectable ~60tps. No cloud costs. Love it.

Federico Viticci

@viticci

Founder and Editor-in-Chief @MacStoriesNet. Writer, podcaster, and builder. I write about Apple and AI. Get more MacStories:

加入 February 2009

1.3K 正在關注 84.2K 粉絲

Federico Viticci@viticci

2026.09.15 12:28

The latest oMLX release by @jundotkim is terrific. Finally can use a local model (qwen3.8-flash-next-q4) running on my M3 Ultra Mac Studio, from my iPhone (with Open Minis) to do "real" assistant work. Running at a respectable ~60tps. No cloud costs. Love it.