Note: you are probably running a distilled version of R1, which is actually LLam... | Hacker News

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

		zbendefy on Jan 29, 2025 \| parent \| context \| favorite \| on: Why DeepSeek had to be open source Note: you are probably running a distilled version of R1, which is actually LLama or Qwen further trained on the input/output of R1. The full R1 is huge (~700GB), altough there are still quantized versions, the smallest one is around 150gb (1.58bit)

9cb14c1ec0 on Jan 29, 2025 [–]

Oh, that's interesting. I didn't know that the ollama version wasn't the whole thing.

postalrat on Jan 29, 2025 | [–]

ollama deepseek-r1:671b is

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