• Unforeseen@sh.itjust.works
    link
    fedilink
    arrow-up
    6
    ·
    15 days ago

    The efficiency improvements in some open models are becoming crazy, like hundreds of times from a year ago. I have a setup such as yours on my framework which can handle a 120b param model fully loaded. It’s capable of the RAG setup you are already envisioning.

    • Mika@piefed.ca
      link
      fedilink
      English
      arrow-up
      1
      ·
      15 days ago

      If you are capable of running 120b, the mistral cli bigger open source model in agentic mode could be available to you.

      How much did your setup cost, if you don’t mind to disclose such information?

      • Unforeseen@sh.itjust.works
        link
        fedilink
        arrow-up
        2
        ·
        edit-2
        14 days ago

        I mentioned my spec above, and I added a 2tb m2, noctua upgrade and a couple expansion modules for the front. I preordered it around 6 months back so before any of the craziness. It was around $3600 CAD

        Edit: also thank you. I have been busy making workflows and haven’t looked at the models in a bit. I’ll check out mistral

        • Mika@piefed.ca
          link
          fedilink
          English
          arrow-up
          2
          ·
          14 days ago

          That’s a good value! I was worrying something running mid power LLMs would cost 10k+ today. Sure ram screwup nuked the field, but it’s also not on the top list of my priorities. So it gives me hope that by the time I would be ready it would be in even better shape.