“There’s no way to get there without a breakthrough,” OpenAI CEO Sam Altman said, arguing that AI will soon need even more energy.

  • FractalsInfinite@sh.itjust.works
    link
    fedilink
    English
    arrow-up
    5
    ·
    11 months ago

    I can already locally host a pretty decent ai chatbot on my old M1 Macbook (llama v2 7B) which writes at the same speed I can read, its probably already possible with the top of the line phones.

    • Petter1@lemm.ee
      link
      fedilink
      English
      arrow-up
      3
      ·
      edit-2
      11 months ago

      Lol, “old M1 laptop” 3 to 4 years is not old, damn!

      (I have running macbookpro5,3 (mid 2009) on Arch, lol)

      But nice to hear that M1 (an thus theoretically even the iPad, if you are not talking about M1 pro / M1 max) can already run llamma v2 7B.

      Have you tried the mistralAI already, should be a bit more powerful and a bit more efficient iirc. And it is Apache 2.0 licensed.

      https://mistral.ai/news/announcing-mistral-7b/

      • TheRealKuni@lemmy.world
        link
        fedilink
        English
        arrow-up
        3
        ·
        11 months ago

        But nice to hear that M1 (a thus theoretically even the iPad, if you are not talking about M1 pro / M1 max) can already run llamma v2 7B.

        An iPhone XR/XS can run Stable Diffusion, believe it or not.

      • FractalsInfinite@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        2
        ·
        edit-2
        11 months ago

        3 to 4 years is not old

        Huh, nice. I got the macbook air secondhand so I thought it was older. Thanks for the suggestion, I’ll try mistralAI next, perhaps on my phone as a test.