• morrowind@lemm.ee
      link
      fedilink
      English
      arrow-up
      3
      ·
      3 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
        ·
        3 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.