Re:Ripple-65B Preview: U.S. Open-Weight SOTA on Agentic Coding
by julianlam on Wednesday November 04, 2026 @08:33PM
(#50373917)
Something doesn't seem right. Vanilla llama.cpp can hit 50 t/s on an R9700. Q6 (albeit with limited context of 64k, more if kv cache is quantized) fits entirely on the card.
[ Parent
| on HN ]
There are no comments on this comment yet.