‹ BackHN Continuity

Thread

Shapelearn Qwen 3.8 27B (13.1 GB VRAM)

104 points · 39 comments · syntaxing

  1. _ache_ · · focus · HN ↗
    From my own test. It's not faster than the unsloth model.

    Disclarer: I'm unsing Vulkan on an AMD GC.

    1. Systemerror7A69 · · focus · HN ↗
      AMD 7900 XTX with Vulkan here as well, wasn't faster on my test either. Might be much different on Nvidia though.

      I assume the limit for me is memory bandwith, as the 7900 XTX has the same bandwith as the 3090 from what I can gather and I already reached ~60 t/s with Unsloth. Those would fit with the numbers Byteshape has for their cards.

      4090 and 5090 have much higher bandwith apparently, so on those cards you can probably get much more out of the kinds of performance improvements they are doing.

      1. MrDrMcCoy · · focus · HN ↗
        Would you consider sharing your config? I can't get anywhere near that with my Strix Halo, nor my AI Pro 9700 XT.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.