• Snort_Owl [they/them]@hexbear.net
    link
    fedilink
    English
    arrow-up
    20
    ·
    edit-2
    18 hours ago

    It’s not magic these models are big and you can’t just squeeze them onto smaller devices. Quantisation isn’t magic either it’s literally reducing the accuracy of a larger model to fit on a smaller device reducing its performance. If the data doesn’t exist in the model weights then the model will perform worse and you can only compress data so much. The only meaningful tech shift in the space is unified memory but it’s not going to be enough for anything this is fundamentally going to need silly quantities of ram for any effective model to run.

    • Chana [none/use name]@hexbear.net
      link
      fedilink
      English
      arrow-up
      5
      ·
      11 hours ago

      The main limitation is just RAM on the GPUs. Unfortunately the bubble itself drove up prices on that exact thing dramatically but this not a particularly expensive thing normally.

      • ashinadash [she/her]@hexbear.net
        link
        fedilink
        English
        arrow-up
        7
        ·
        11 hours ago

        normally.

        GPU prices shot up in ~2018 and 2020 and [etc] and never came back down. Nowadays a 9060XT (the useful version, mind) costs on its own what a decent entry level PC used to. We are never going back to normal.


        Remember to enable JPEG-XL support in your browser, even on your phone!