Qwen3.6-35B-A3B is worse than 27B because it's an MoE and 27B is dense. 35B only... | Hacker News

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

zargon 77 days ago | parent | context | favorite | on: Qwen 3.6 27B is the sweet spot for local developme...

Qwen3.6-35B-A3B is worse than 27B because it's an MoE and 27B is dense. 35B only passes each token through 3B of its total parameters, whereas 27B sends each token through all 27B parameters.

naikrovek 76 days ago [–]

I did not know that, thank you. I should have known that probably, but I'm new to all of this.

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