Btw somebody should report numbers of DwarfStar running DS4.1 Flash on a 256GB M5 Ultra, so see what the speed difference is. Agreed on thermals btw, even if there are ways to avoid most problems actually... But instead of talking about them I'll simply implement them :D
If you think at it, there are very little reasons to spend the same money for a Mac Studio M5 Ultra with 256GB of RAM if you can get, for the same price, 2x Macbook Pro with 128GB RAM and an RDMA cable. It is just a matter of developing good inference software. Do you agree?