Jeez, I thought I could get away with q8_0 KV cache. Guess not. | Hacker News

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

arcanemachiner 27 days ago | parent | context | favorite | on: Why your local LLM feels dumber than it is

Jeez, I thought I could get away with q8_0 KV cache. Guess not.

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