‹ BackHN Continuity

Thread

Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s

816 points · 361 comments · snehesht

  1. cuvinny · · focus · HN ↗
    Haven't had time to do much quality testing but the IQ2 model is running at 65 tps on a 9070xt/5900x. That is wild.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.