I'm running it using a 4090 on using llama.cpp with Q5_K_S and its running at ~3... | Hacker News

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

ixaxaar 25 days ago | parent | context | favorite | on: Qwen 3.8 27B

I'm running it using a 4090 on using llama.cpp with Q5_K_S and its running at ~33 t/s

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