NVidia should be afraid. Same GB/s on CPU are much more than on GPU. The problem here will be the price of the whole system. Anyway it's a step in the right direction if we want something like Copilot on premises or at home.
Just curious, much more what?
Most of the SIMD code I write can consume tens of GB/s BW per core. From this perspective, it seems that 192 cores make for an imbalanced system.