35b A3b runs ~100 tokens a second on the best M5 Max gpu setup. | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

jaggederest 81 days ago | parent | context | favorite | on: Qwen 3.6 27B is the sweet spot for local developme...

35b A3b runs ~100 tokens a second on the best M5 Max gpu setup.

ctkhn 80 days ago [–]

I got around 50-60 on my m3 max so 100tps seems very realistic for 2 gens later of chip and double the ram

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact