M3 max tflops is tiny compared to the 12k box. It's not even comparable.

It is very comparable if you work out the $/tok/s on inference. I did some napkin math and it looks like you’re getting roughly 3x the performance for 3x the cost. Red v2 vs Mac Studio M3 Ultra 96GB.

If you compare tokens/kWh efficiency then my math has Mac Studio being about 1.5x more efficient.

M3 has tolerable decode performance for the price, and that's what people would care about most of the time. they underperform severely wrt. prefill, but that's a fraction of the workload. AI, even agentic AI, spends most of its time outputing tokens, not processing context in bulk.