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

Also the 3588 chips can run LLMs on the NPU.

Not quite llama.cpp level easy but definitely doable.

For 7B class models the speed is usable



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: