`model.safetensors` for Qwen3-0.6B is a single 1.5GB file. Qwen3-235B-A22B has 1... | Hacker News

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

		smcnally 11 months ago \| parent \| context \| favorite \| on: Everything we announced at our first LlamaCon `model.safetensors` for Qwen3-0.6B is a single 1.5GB file. Qwen3-235B-A22B has 118 `.safetensors` files at 4GB each. There are a bunch of models and quants between those.

azinman2 11 months ago [–]

Does it run in 8x80G? Or does the KV cache and other buffers push it over the edge?

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