‹ BackHN Continuity

Thread

Qwen3.8 Max now ranked as the best overall model by agentic index

252 points · 127 comments · apitman

  1. syntaxing · · 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. tarr11 · · focus · HN ↗
      What type of agentic tasks are you using it for (eg how complex)?
      1. syntaxing · · focus · HN ↗
        For personal stuff, I use it with AnythingLLM. It replaced any Google search for me. For coding, I run opencode though I have been debating switching to Pi.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.