• BJW@lemmus.org
    link
    fedilink
    English
    arrow-up
    1
    arrow-down
    3
    ·
    1 day ago

    You are mistaken. Power consumption is lower because the VRAM is what’s primarily being utilized, not the GPU. Not only that, but GPU & VRAM are used non-stop while gaming, but only intermittently while performing LLM inference. And it’s asynchronous, only processing when replying, while the rest of the time it’s idle, while waiting for the next prompt. Gaming uses a LOT more electricity than local LLM usage.

    If you’re going to count the processes that had to occur prior to the current usage, then gaming uses a magnitude more electricity because of all the electricity of the developers who made the game, and the artists, and the sound designers, and the composers, and the compilers, etc.

    Let’s just leave it at both use substantial energy, and both are difficult to justify. I still personally love and will use both, as a game developer with a focus on novel AI usage in games.

    • tyler@programming.dev
      link
      fedilink
      English
      arrow-up
      1
      ·
      8 hours ago

      The temperature my computer room gets to when gaming vs using a local model says otherwise. I’ll gladly plug in a measuring tool and show you the data if you want.

      • BJW@lemmus.org
        link
        fedilink
        English
        arrow-up
        1
        ·
        7 hours ago

        That depends entirely on the hardware, the game, the model, and the prompt. I’m sure you could find a combination where the LLM power usage is higher than the game, just as I could do the opposite. The point is, they both use power, but only one of them is disparaged.