DeepSeek v4.1 Flash avg 102 tps on 4x RTX6000 pro max-q, 2.1x up from v4-flash
By ambientlight · 2026-09-18 · 2 points · 2 comments
https://forum.level1techs.com/t/llm-inference-workstation-4x-rtx6000-blackwell-pro-max-q-384gb-vram-threadripper-pro-7985wx-wrx90e-sage-se-512gb-ram-1700w/252181
By ambientlight · 2 points · 2 comments · on Hacker News, read on BetterNews.
Open the full discussion on BetterNews