1.2 TB/s of bandwidth is faster than any consumer GPU available today like 4090 etc. I don;t know what you've been drinking.
They don’t need us to give them ideas. Everyone and their mother are buying up macs with the intention to run opensource models. Its the best price/performace ratio you can get.
5090 is ~1.8 TB/s and the RTX PRO was somewhat affordable for what it was at $8,000-10,000 street. Not now; prices just doubled.
To be fair, still looks like a bargain compared to the $55,000 Mac Pro 2019 +$6000 display and $1000 display stand.
VRAM is where it would help. You can have the fastest gpu in the world but if it has 8gb of RAM, it would be pretty much useless. More RAM means it can hold bigger models in it’s memory. Better models are all larger than what consumer level GPUs can hold.
Speed is not the only thing that matters. Try running AI image or video models in ComfyUI on Mac and you will quickly find that they either don't run at all, they run on the CPU only, or they run on the GPU but an order of magnitude slower than what you'd expect simply because everything is optimized for CUDA and nothing is optimized for Mac. So you can chain any number of Mac Studios together and you still won't get anywhere near CUDA because the issue is not speed or performance, it's the ecosystem that nVidia has built out. The 4090 may be much slower on paper but it will actually run all the image models and it will do so pretty fast as opposed to the Mac. Every week there are optimizations coming out for CUDA, making generation twice as fast, 10 times as fast, etc... While the top end Macs are still far slower than even the slowest nVidia GPU – and this has nothing to do with RAM, power, or the GPU itself.
I'm not talking about gaming, I'm talking about AI. A gaming PC just happens to have an nVidia GPU usually. AI can be limited by VRAM but as Macs have demonstrated, you can have a lot of VRAM and still be incredibly slow because AI workflows are optimized for CUDA and not Mac GPUs. Open ComfyUI and load up any video or image model and see for yourself: on a high end Mac you'll get maybe 1-5 images per minute while on even the slowest nVidia GPU you'll get 1 image per second. You can optimize for VRAM, with new workflows running under 6 or 8GB of VRAM, that's less of a problem. But if the GPU can't handle it because it's simply incompatible with the software, then you can have all the VRAM in the world and it still won't run, or it will run poorly. Speed and architecture cannot be replaced by just adding more VRAM, you need both, with VRAM being the lesser of the two in order of importance.
This would be an interesting benchmark. A few months ago, I saw a post on some forum about a guy running a comparison of an image analysis pipeline. He ran it for 1000 images and compared a 5090 to a then current Mac Studio and tracked power usage and time. IIRC, the Mac had lower power usage but took about 10x longer to finish the task so total energy consumption was higher.
