2026-11-01 · America/Los_Angeles · 社区动态 · #11

Qwen 3.8 Flash Next NVFP4 on 64gb RAM and 5090, Basalt. Ditched windows for it. Very hyped for qwen 4 model family now.

So, I was asleep on Strata and its specialized forks. Tried basalt and i'm very impressed with the speed/intelligence QFN gives you. Here is my benchmark: https://preview.redd.it/8qhp92ql73zh1.png?width=2946&format=png&auto=webp&s=2abf6d03db5124c8491baf980b8cd3b5367fdb9f I cannot get it to work fast enough with windows, because W11 eats 1.5GB of VRAM and 6GB of RAM. At that point, experts spill to RAM and CPU gets hit hard... decode/prefill drops by 70% because there is not enough of available RAM anyway. Switched experimentally to cachy just to test... and It's amazing that my AI box can…

热度 46.5 / 100；排名与评分保留该期记录。