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

It needs a mlx fork because the lowest bit in mlx is 2 currently (for affine quantization).
 help



That mlx is for apple hardware only, though? Or did I misunderstand something.

It needs a llama.cpp fork, too; so the stock runtime (based on stock llama.cpp) used by LM Studio presumably won't work for it.



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

Search: