alt Hacker NewsNo, the AMD ones he’s talking about allow the GPU to address that memory as well: they’re “APU’s” that share system RAM as GPU memory
That said the compute power of the GB10 is awesome, my DGX Spark-like has been better than I expected.
Replies
giancarlostoro • yesterday at 10:15 PM
That's the thing, my understanding is that these Nvidia ones are supposed to have very impressive performance.
➕ show 1 reply
Depending on what you are doing you may find all the models are written for CUDA though. I'm playing with gaussian splatting and it's like that. Codex is doing a good job porting stuff to Metal, but it would be easier & faster if I had Nvidia hardware to just run the models natively.
Not everything with AI is LLMs running on llama.cpp.