It gets similar performance to the old version of the 30B MoE model, but not the... | Hacker News

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

		smallerize 6 months ago \| parent \| context \| favorite \| on: Qwen3-4B-Thinking-2507 It gets similar performance to the old version of the 30B MoE model, but not the updated version. https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507

Imustaskforhelp 6 months ago [–]

I still think that its still very commendable though.

I am running this beast on my dumb pc with no gpu, now we are talking!

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