stewartpark
Re:Ripple-65B Preview: U.S. Open-Weight SOTA on Agentic Coding
on Wednesday November 04, 2026 @09:54PM (#50374544)
That helps, yes. But speculative decoding that requires a secondary/draft model means a trade off (smaller KV pool), so often times the only option left is MTP unless you have lots of VRAM. And as you already know, these options (MTP, DFlash, DSpark, etc) are also available for MoE models, too. If it's 3tk/s instead of 1tk/s, we can say it helps but not sure how many people would be excited about that. I'd be more excited about 150tk/s instead of 50tk/s!
Re:Ripple-65B Preview: U.S. Open-Weight SOTA on Agentic Coding
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!
Re:Ripple-65B Preview: U.S. Open-Weight SOTA on Agentic Coding
on Wednesday November 04, 2026 @03:51PM (#50371331)
I think it's because the primary users of this model won't even look at "those other open weight models" as options. This is the right chart to present to those who would consider this model. (e.g. US Gov't agencies, chip design industry, etc etc)
Re:Ripple-65B Preview: U.S. Open-Weight SOTA on Agentic Coding
on Wednesday November 04, 2026 @03:36PM (#50371154)
It's great to see another competitive open weight model. Congratulations!
But as is, it's probably hard to become popular amongst hobbyists and local model enthusiasts like Qwen's 27B class models or MOE models because it's a 65B dense model and inference will be prohibitively slow on consumer grade hardware, and seems like the goal/mission of the company behind this model is to automate chip design.
So if I have to assume and connect the dots, this is for the companies who want to use AI in air-gapped environments for chip design so that they protect their IPs (not leaking to third party AI labs/hostile parties) and can afford lots of server grade inference hardware for a quick unlock with the big dense model.
Neat!
Re:Ask HN: Is a master degree in CS worth it
on Sunday January 29, 2017 @01:35PM (#13515757)
I think that also depends. What makes you think that self-taught applicants can't learn compilers, distributed systems, or machine learning? If the candidate has proven the same amount of knowledge acquired during the interview, I'd definitely go for the self-taught one.