MI300X
AMD's first broadly deployed AI GPU and the canonical case study in the gap between paper FLOPS and realized throughput once the software stack is accounted for.
Current numbers
192 GBMI300X HBM3 @ 5.3 TB/s, 750 W (CDNA 3) — 2.4x H100 capacity; MI325X 256 GB @ 6 TB/s, 1,000 W