My understanding is that models are currently undertrained and not very "dense",... | Hacker News

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

		nenaoki 4 months ago \| parent \| context \| favorite \| on: Qwen2.5-VL-32B: Smarter and Lighter My understanding is that models are currently undertrained and not very "dense", so Q4 doesn't hurt very much now but it may in future denser models.

anon373839 4 months ago [–]

That may well be true. I know that earlier models like Llama 1 65B could tolerate more aggressive quantization, which supports that idea.

Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact