‹ BackHN Continuity

Thread

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

741 points · 330 comments · snehesht

  1. kamranjon · · focus · HN ↗
    Dwarfstar already supports this, curious how it compares, but I use the q4 quant daily and it works really well.

    <a href="https:&#x2F;&#x2F;github.com&#x2F;antirez&#x2F;ds4&#x2F;blob&#x2F;main&#x2F;docs&#x2F;MODELS.md#qwen38-flash-next" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;antirez&#x2F;ds4&#x2F;blob&#x2F;main&#x2F;docs&#x2F;MODELS.md#qwen...

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.