• morrowind@lemm.ee
    link
    fedilink
    English
    arrow-up
    4
    ·
    13 hours ago

    good luck trying to run a video model locally

    Unless you have top tier hardware

    • brucethemoose@lemmy.world
      link
      fedilink
      English
      arrow-up
      4
      ·
      13 hours ago

      1.4B should be surprisingly doable, especially once quantization/optimized kernels are figured out.

      HunyuanVideo can already run on a 12GB desktop 3060.