Would second this, I switched to oMLX I get ~75 tok/s on Qwen3.6-35B-A3B-4bit on... | Hacker News

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

mc8098 14 days ago | parent | context | favorite | on: Qwen 3.8 27B is excellent, but it defaults to over...

Would second this, I switched to oMLX I get ~75 tok/s on Qwen3.6-35B-A3B-4bit on a 48GB M5 Pro

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