News for hackers. Stuff that matters.
Re:Ripple-65B Preview: U.S. Open-Weight SOTA on Agentic Coding by stewartpark on Wednesday November 04, 2026 @06:09PM (#50372742)
I hear what you're saying - there are people who will use it even at 0.1 tokens/s and run tasks over night or over multiple days if it is good. but Qwen3.8 Flash Next is a MoE model (6B active) so the memory bandwidth/compute required to calculate each token is very different from a 65B (meaning, 65B all active) dense model!

There are no comments on this comment yet.