• ag10n@lemmy.world
    link
    fedilink
    English
    arrow-up
    5
    ·
    4 hours ago

    What’s the cost of the compute you have to run something locally?

    Majority of people don’t have 32G of vram to run something remotely as capable

    • MrQuallzin@pie.eyeofthestorm.place
      link
      fedilink
      English
      arrow-up
      8
      arrow-down
      1
      ·
      3 hours ago

      I’ve got an old 1060ti in my server. Ollama shares it with just a couple other containers. Electricity here is majority hydro with some natural gas, $0.08/kWh.

      It’s a little slow, but I can comfortably run qwen3:14b. Of course that’s not all done on the GPU, a large part is offloaded to server ram (generally 32GB available so more than enough headroom)

      My server and my gaming PC combined last month came out to $13.32

      • ag10n@lemmy.world
        link
        fedilink
        English
        arrow-up
        3
        ·
        edit-2
        3 hours ago

        How does that compare to closed models that Anthropic offers, at the context and scale they offer.

        I run Qwen3.6 27B locally and it’s usable with 16G vram but still not the same as a data centre of Blackwell clusters.

      • ag10n@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        ·
        3 hours ago

        Describe greased lightning, because it’s much slower and needs to handle compression for context

        We’re moving in that direction but an M5 is not what the majority of people are running at home

        • greyscale@lemmy.grey.ooo
          link
          fedilink
          English
          arrow-up
          1
          ·
          37 minutes ago

          I dunno man, I’m not a slopjockey so I don’t know the minutiae of the addiction.

          All of our devs appear to have M5s right now. All of those copilot+ laptops have NPUs too.

          • ag10n@lemmy.world
            link
            fedilink
            English
            arrow-up
            1
            arrow-down
            1
            ·
            15 minutes ago

            Your company has bought you the latest and greatest and likely supports commercial token usage too

            You can’t compare LLMs at scale to running it locally; same experience and capabilities

            • greyscale@lemmy.grey.ooo
              link
              fedilink
              English
              arrow-up
              1
              ·
              6 minutes ago

              “Latest and greatest” my fucking sides lmao

              My company gave me some US shitware and I’ve got some local shitware instead.

              If you can’t make that work and are dependent on the teat of the slopgenerators, that’s a skill issue on you, buddy.

    • blackbeans@lemmy.zip
      link
      fedilink
      English
      arrow-up
      3
      arrow-down
      2
      ·
      edit-2
      3 hours ago

      I remember my computer not being fast enough to even play an MP3 file. Two years later, my computer was capable of running 3D accelerated games, browsing the internet at broadband speeds and playing videos.

      Sometimes technology advances fast. We could be entering such an era as there are major investments taking place and global competitors will rise to the occasion to market these to a broader audience.

      I think it will be entirely possible for consumers to use a decent LLM on their computer in a few years time.

      • ag10n@lemmy.world
        link
        fedilink
        English
        arrow-up
        3
        arrow-down
        1
        ·
        3 hours ago

        It’s not the 90s anymore. Unless there’s a compression algorithm putting billions of relationships into a manageable size, local AI is highly specific under 8G vram (text-to-speech as an example is under 1G) let alone the context required for keeping a conversation or writing code.

        • blackbeans@lemmy.zip
          link
          fedilink
          English
          arrow-up
          1
          arrow-down
          2
          ·
          3 hours ago

          To be clear, I wasn’t talking about a leap in LLM design. I was talking about a leap in hardware capabilities…

          • KRAW@linux.community
            link
            fedilink
            English
            arrow-up
            2
            ·
            1 hour ago

            Improved hardware capabilities used to come very quickly (see Moore’s Law and Dennard Scaling). However that trend is basically over, so getting higher performance hardware takes a lot of effort to make hardware specialized for certain tasks. That’s why you see there inference accelerators like Groq, SambaNova, Cerebrus, etc. However this is hardware that still is gonna go into data centers. Something innovative has to happen on the AI side for commercial-grade models to be runnable on consumer hardware.

          • ag10n@lemmy.world
            link
            fedilink
            English
            arrow-up
            2
            ·
            3 hours ago

            Which are increasingly out of reach for a normal person. Phones let alone PC hardware have increased exponentially in recent history