• LeTak@feddit.org
    link
    fedilink
    English
    arrow-up
    4
    arrow-down
    1
    ·
    12 hours ago

    I play Minecraft with the PrismLauncher on the M4 24GB. Shaders and DistantHorizon. 50-80fps

    AI also works. Gemma 4 26B a4b MLX runs… somehow.

    • REDACTED@infosec.pub
      link
      fedilink
      English
      arrow-up
      1
      ·
      3 hours ago

      Yeah, I played large modpacks at good fps decade ago.

      It’s not about whether you can use AI (obviously they can, commonly even larger models than similar laptops due to unified memory), it’s about how fast it is.

      • LeTak@feddit.org
        link
        fedilink
        English
        arrow-up
        1
        ·
        1 hour ago

        Gemma ran at 50/tops Qwen 27B? was way slower , 5/tops 8B models run perfectly fine, but are mostly useless for chat and agents. 8B is only good for specialists. Like one 8B model that can only write and correct python3 code. And then only in English.