• setVeryLoud(true);@lemmy.ca
    link
    fedilink
    English
    arrow-up
    2
    ·
    23 hours ago

    Maybe not a mobile device, but running decent local models is definitely within reach for the average consumer today by simply adding a GPU with lots of VRAM to their existing PC.

    • Squizzy@lemmy.world
      link
      fedilink
      English
      arrow-up
      3
      ·
      20 hours ago

      I mean yes but those gpus are not necessarily within reach of the average consumer anymore. Even if you got one for a grand which is a lot of money you would have cooling and enclosure costs, possibly additional hardware.

        • Squizzy@lemmy.world
          link
          fedilink
          English
          arrow-up
          3
          ·
          15 hours ago

          Thats is pretty decent alright, I had heard 24 was what was needed for decent local AI.

          • setVeryLoud(true);@lemmy.ca
            link
            fedilink
            English
            arrow-up
            2
            ·
            15 hours ago

            24 is ideal, 16 works fine especially with some MoE offloading. If you use llama-swap, a fast PCIe bus and fast storage is ideal. Takes about 20 seconds to swap between two models on my X570 board.