Apple M2 Ultra Isn't Faster Than Last Gen AMD&Intel Desktop CPUs, 50% Slower GPU

Re:Apple M2 Ultra Isn't Faster Than Last Gen AMD&Intel Deskt... by sunflowerfly on Saturday June 10, 2023 @03:12PM (#36273948)

One differentiator is the amount of memory available. Apple's shared pool of memory means the GPU has potentially up to 96gb of ram at its disposal, where discrete GPU's are often limited to 8, 12, 16, etc. They mentioned in the keynote that the M2 can handle many tasks discrete GPUs cannot simply because they run out of ram.

[ Parent | on HN ]

Re:Apple M2 Ultra Isn't Faster Than Last Gen AMD&Intel Deskt... by incrudible on Saturday June 10, 2023 @04:02PM (#36274487)

$15,000 will buy you an A100 with 80GB of RAM at 2TB/s that will annihilate the biggest Apple chip.

[ Parent | on HN ]

Re:Apple M2 Ultra Isn't Faster Than Last Gen AMD&Intel Deskt... by ElFitz on Saturday June 10, 2023 @05:47PM (#36275501)

Sure, but then that’s the price of multiple entire laptops. Or 2 Mac Pros. Not sure what point you’re trying to make here.

[ Parent | on HN ]

Re:Apple M2 Ultra Isn't Faster Than Last Gen AMD&Intel Deskt... by incrudible on Saturday June 10, 2023 @07:43PM (#36276502)

It is also the performance of 4 Mac Pros. GP was talking about tasks that dedicated GPUs supposedly could not handle. Who is is running models needing 60+ GB of VRAM on their laptops?

[ Parent | on HN ]

Re:Apple M2 Ultra Isn't Faster Than Last Gen AMD&Intel Deskt... by ElFitz on Saturday June 10, 2023 @09:36PM (#36277096)

Some have had fun running some of the larger Llama, Vicuna & Guanaco models on their MacBooks. Mostly to experiment with local inference.

Although quantisation has now lowered the required memory, I wouldn’t be surprised if it comes in handy again in the near future.

But today that’s quite a niche use case.

[ Parent | on HN ]