Let's not pretend these are machines for hardcore computing jobs which belong on servers in terms of work/cost. Apples laptops are still amazing because we can do crazy amounts of work quickly without running out of battery. The edit, recompile, test loop is fast for programmers equipped with these expensive machines. And you can carry them everywhere without much risk of failure.
I don't think anyone is pretending that a Macbook Pro can compare to 8 H100 cards from Nvidia in terms of LLM training or for serving LLMs. But you can buy an awful many macbooks for the price of 8 H100 GPUs.
But if your workload belongs on 8 H100 GPUs then there isn't much point in trying to run it on a macbook. You'd be better served by renting them by the hour, or if you have a quarter million dollars you can always just purchase them outright.
The H100 is just an example, this is true for any workload that doesn't fit on a laptop.
> And you can carry them everywhere without much risk of failure.
Unless you close the lid on a small grain of sand or some similarly small, hard particle, at which point the screen goes black and costs nearly as much to replace as the 1 year old computer is worth. Ask me how I know. :’(
If you work on scripts that run in a minute or two, it's not worth the hassle of running it on servers. Yet it's long enough that saving 50% is meaningful. I happen to often work on such tasks so I really notice improvements in single and multicore performance.
