By losing performance I meant you don’t need to quantize the model a lot since i... | Hacker News

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

elorant on Aug 15, 2023 | parent | context | favorite | on: Why host your own LLM?

By losing performance I meant you don’t need to quantize the model a lot since it fits in RAM. My bad for not clarifying it.

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