Hacker News
points by yieldcrv 2 hours ago | 0 comments
kapitsa is customized well to just a small selection of models that are in vogue right now, focusing on qwen and nemotron

compared to llama.cpp that tries to cater to all but does so only averagely

check the catalogue and see if one of the quantizations fit

Aún no hay comentarios.
Hacker News