Explainers: Hopper

Nvidia's data-center GPU roadmap, Hopper to Rubin
Nvidia went from Hopper through Blackwell and Blackwell Ultra to Vera Rubin in four years; here is each generation.

Nvidia B200 vs H100: what Blackwell changes
B200 vs H100 from Nvidia's own spec sheets: two dies instead of one, FP4, fifth-generation NVLink and more memory.

Nvidia H100: specs, memory and what it is used for
Nvidia H100 specs: 80 GB HBM3 (SXM) or 94 GB (NVL), FP8 dense and sparse, 700 W per GPU, 10.2 kW per DGX H100.
