‹ BackHN Continuity

Thread

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

741 points · 330 comments · snehesht

  1. lousken · · focus · HN ↗
    lm studio bionic, unsloth, now this... it would be nice if it worked at least in one of those without installing another component
    1. kennywinker · · focus · HN ↗
      I'm sure one of those inference engines will add support for this within a month or so.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.