Thread

1. syntaxing · 1786043706 · focus · HN ↗

   I am so excited for Qwen 3.8 27B. It’s a shame how slow prefill (~3-400) is on a strix halo but it’s such a good model for agentic tasks.

   1. CamperBob2 · 1786044360 · focus · HN ↗

      How are you running it on a Strix Halo? The weights aren't out yet, are they?

      1. syntaxing · 1786044703 · focus · HN ↗

         I meant Qwen3.6. Unsloth supposedly has early preview of the model and the VRAM requirement is the same so most people expect similar model size and type.

Unofficial Hacker News client; not affiliated with Y Combinator.