News for hackers. Stuff that matters.

A comment on Qwen 3.8 27B on my laptop can interpret model weights, too. Parent comment

Re:Qwen 3.8 27B on my laptop can interpret model weights, too by irthomasthomas on Wednesday November 04, 2026 @04:30AM (#50363169)
Why use llamacpp instead of something faster like exllama?
[ Parent | on HN ]

There are no comments on this comment yet.