This 61GB one: https://ollama.com/library/qwen3:30b-a3b-fp16 You can see it's ro... | Hacker News

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

		rahimnathwani 3 months ago \| parent \| context \| favorite \| on: Qwen3: Think deeper, act faster This 61GB one: https://ollama.com/library/qwen3:30b-a3b-fp16 You can see it's roughly the same size as the one in the official repo (16 files of 4GB each): https://huggingface.co/Qwen/Qwen3-30B-A3B/tree/main

int_19h 3 months ago [–]

fp16 is overkill though. 8-bit is the sweet spot before perf degradation starts getting noticeable.

rahimnathwani 3 months ago | [–]

I haven't yet seen any evals comparing the original Qwen3-30B-A22B with https://ollama.com/library/qwen3:30b-a3b-q8_0

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