Title says it all. I’m planning to get an M2 Mac Studio soon. Personally, I’m still coming to a decision on the following SoC & RAM options:

SoC:

  • M2 Ultra with 24-core CPU, 60-core GPU, 32-core Neural Engine
  • M2 Ultra with 24-core CPU, 76-core GPU, 32-core Neural Engine

RAM:

  • 128GB
  • 192GB

To current M2 Studio owners, how did you choose your specs and why? Also could you comment on real world performance with regards to your workflow(s)? Thanks! :)

  • 0x0001@sh.itjust.works
    link
    fedilink
    arrow-up
    11
    ·
    1 year ago

    I went all out and got the 192, I’ve been using it to run local machine learning models successfully. Llama2 70b runs fairly well after quantizing to 16 instead of the original 32 which ate all 192GB and 40GB of swap before running out of system memory. Smaller models like the llama2 7b are wicked fast.

    Performance as far as normal development goes is simply divine, I can have basically every project I ever work on open on my dual 4k monitors without any slowdown ever. Simultaneously compiling and running models in the background without a stutter.

    My biggest complaint so far is with my thunderbolt 4 dock not supporting 144hz my monitors can crank out.

    I have had one system crash so far, not sure of the cause, but overall stability has been impeccable.

    I’m used to x86 machines, one flaw with the apple silicon switch in general is that some of my react native libraries were compiled in a way that make it difficult to compile without rosetta, that’s obviously not apple’s problem, nor is it specifically a studio issue.

    9k was incredibly painful, but I’m happy to have a machine that outperforms most retail machines on the market for vram and machine learning without spending even more.

  • matthewc@lemmy.self-host.site
    link
    fedilink
    arrow-up
    7
    ·
    1 year ago

    Developer here. Completely depends on your workflow.

    I went base model and the only thing I regret is not getting more RAM.

    Speeds have been phenomenal when there binaries are native. Speeds have been good when the binaries are running through Rosetta.

    The specs you’re wavering between are extremely workflow specific. You know if your workflow requires the 16 extra GPU cores. You know if your workflow requires another 64 GB of RAM.

      • dszp@artemis.camp
        link
        fedilink
        arrow-up
        1
        ·
        1 year ago

        My M2 Max MBP with 64GB RAM can have a decent chunk of apps open while handling 1500 open browser tabs in about 50GB of RAM with no swap. As an example. Used quite a bit of swap on my M1 16GB previously.

  • satanmat@lemmy.world
    link
    fedilink
    arrow-up
    2
    ·
    1 year ago

    I’ve got an m2 MBP. But I’ve never heard the fans turn on. Ever.

    This is a business purchase?

    Do the math? Over the course of the next year will you save / or be able to bill the difference?

    There’s a rough $2000 difference between them.

    You bill at $100/ hr. That’s 20 hours of work/ time off you’ll earn

    Will you make tat in the next year?

    Yeah. I’d say splurge on the higher specs

  • reallynotnick@lemmy.world
    link
    fedilink
    arrow-up
    2
    ·
    1 year ago

    I mean for RAM I’d just look at what you are currently using when working by pulling up Activity Monitor and seeing if you have a ton of swap going on. And then figure out how long you plan on using the system and add some buffer assuming RAM needs will increase over time.