• gravitas_deficiency@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        2
        ·
        3 days ago

        Like, I get the value proposition of more open hardware… but Apple is absolutely killing it in terms of low to mid tier homelab ML-oriented boxes. They straight up work better, and require near zero custom configuration - and zero kernel hacking.

          • GenderNeutralBro@lemmy.sdf.org
            link
            fedilink
            English
            arrow-up
            2
            ·
            2 days ago

            Asahi only runs on M3 and older though. The last three generations of Macs have no native Linux support as far as I know. You can run ARM-native Linux VMs, but you can’t boot directly to Linux.

            • muusemuuse@sh.itjust.works
              link
              fedilink
              English
              arrow-up
              2
              ·
              2 days ago

              Asahi is not done. It’s still ongoing, and their progress has been faster than anything we’ve seen on snapdragon.

              • GenderNeutralBro@lemmy.sdf.org
                link
                fedilink
                English
                arrow-up
                2
                ·
                6 hours ago

                100% respect for the Asahi devs. I fully expect the situation will improve, but I wouldn’t buy an M6 on the hope that I’d get native Linux in the near future. If I wanted to go that route I’d just look for a used M3.

                Qualcomm has announced official Linux support with the X2 line, so I think we can expect a much faster turnaround from here on out.

                • muusemuuse@sh.itjust.works
                  link
                  fedilink
                  English
                  arrow-up
                  1
                  ·
                  5 hours ago

                  Qualcomm announced support for the chips used in the ARM surface and then backed out. I’m still rocking a used MacBook Pro M1 pro and it’s been great.

  • [object Object]@lemmy.ca
    link
    fedilink
    arrow-up
    2
    ·
    3 days ago

    A bit expensive to get test drivers, learned that from amd.

    Lots of ports, seems pretty good, the AI features are fucking stupid though “you can run openclaw on it” okay… you can run openclaw on most anything, what models can it run on low memory and a low power NOU? Realistically you can do fine embedding, but you won’t get realtime VTT or TTS or usable agents with openclaw.