I imagine the gguf is quantised stuff? | Hacker News

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

		exe34 51 days ago \| parent \| context \| favorite \| on: Running GPT-OSS-120B at 500 tokens per second on N... I imagine the gguf is quantised stuff?

DrPhish 51 days ago [–]

No, I’m running the unquantized 120b

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