[throwawayffffas]

You get 8 nvmes set them up in raid 0/1 across two full pcie5x16 ports and you could reach up to 4ish tokens per second, presumably.

[withinboredom]

The problem is dram bandwidth to the cpu. Each token costs roughly 20gb of traffic and ddr5 is roughly 50-80gb/s, plus you still have to run the compute sequentially. That’s your limit.