they responded to my tweet last year and said they didn't quantize the models. | Hacker News

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

		behnamoh 3 months ago \| parent \| context \| favorite \| on: Deepseek R1-0528 they responded to my tweet last year and said they didn't quantize the models.

boroboro4 3 months ago [–]

It's very hard to find right now but I'm sure they said they don't quantize KV cache, but their weights are in fp8.

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