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. tarr11 · 1786044196 · focus · HN ↗

      What type of agentic tasks are you using it for (eg how complex)?

      1. syntaxing · 1786048839 · 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.
   2. CamperBob2 · 1786044360 · focus · HN ↗

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

      1. 13rac1 · 1786044572 · focus · HN ↗

         I interpret @syntaxing as meaning they are looking forward to running Qwen3.8-27B, but are frustrated by prefill times with other models, such as Qwen3.6-27B.
      2. 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.
   3. LoganDark · 1786045583 · focus · HN ↗

      I find that 35B-A3B is much easier to run on my M4 Max (both prefill and generation)

      1. markasoftware · 1786046091 · focus · HN ↗

         It's well known 35b is much faster (on any hardware) and quite a bit dumber
   4. colingauvin · 1786046414 · focus · HN ↗

      Prefill is survivable if you cache well. But what kills me is the context. Qwen 27 needs a ton of room for KV Cache. I guess not an issue on a 128 GB Halo or Spark, but if you are running of consumer/prosumer GPUs it's miserable to be compacting every 120k tokens.

Unofficial Hacker News client; not affiliated with Y Combinator.