Glad they set a time rather than leaving it open

  • Avid Amoeba@lemmy.ca
    link
    fedilink
    English
    arrow-up
    3
    ·
    edit-2
    3 days ago

    I don’t think you can run 27B on 16GB without degrading its quality. You’d have to drop to lower quantization. Is there some new magic?

    35B A3B runs well on 8 and 16GB GPUs.

    • SirDimples@programming.devOP
      link
      fedilink
      English
      arrow-up
      6
      ·
      3 days ago

      Everything runs well if one is patient enough 😂

      But yeah, with a smaller context and carefully offloading some of the layers to the CPU, it’ll run just not very fast. And definitely using Q4 quants.

      • e0qdk@reddthat.com
        link
        fedilink
        English
        arrow-up
        2
        ·
        3 days ago

        Everything runs well if one is patient enough 😂

        I mean, if you’re really patient you can even run with CPU only as long as you have enough RAM… My ~decade old computer with DDR3 RAM gets 14 tok/s prompt processing and ~5 tok/s decode on MoE models (e.g. a Qwen 3.6 35B-A3B variant at Q6_K – my current default model). That pp tok/s is painfully slow… but it still works!

        Same computer, same model but using a discrete GPU that can fit all the weights on the card – ~900 tok/s prompt processing, ~70 tok/s decode.

    • MalReynolds@slrpnk.net
      link
      fedilink
      English
      arrow-up
      5
      ·
      3 days ago

      Yeah, down to 4bit, which works OK, but 35BA3B is much more performant. Sometimes you want the monolithic quality and damn the speed…