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

This person claims to have compared llama.cpp against gpt-fast on a 4090, and found gpt-fast about 20% faster.

https://twitter.com/zeuxcg/status/1730450360895242355




Awesome, thanks!




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

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

Search: