• peopleproblems
    link
    English
    88 months ago

    How big are they, and what do I need to use them well?

    • @joneskind
      link
      English
      2
      edit-2
      8 months ago

      Most of 7b-8b models run just fine in 4bits quant and won’t use more than 4 or 5 GB of VRAM.

      The only important metric is the amount of VRAM as the model must be loaded in VRAM for fast inference.

      You could use CPU and RAM but it is really painfully slow.

      If you got an Apple Silicon Mac it could be even simpler.

      • Venia Silente
        link
        fedilink
        English
        28 months ago

        I have an Intel Celeron Mobile laptop with iGPU and, I think, 256MB VRAM. How many bs does that get me for the LLM?

        Only half-joking. That’s my still functional old daily driver now serving as homelab

        • @joneskind
          link
          English
          28 months ago

          Well, I got a good news and a bad news.

          The bad news is you won’t do shit with that my dear friend.

          The good news is that you won’t need it because the duck is back.