AI chip explainers
Explainers on AI chips: data-center GPU generations, custom accelerators, HBM, the supply chain and export rules.
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.
H100 rental price: what clouds charge per GPU-hour
The H100 rental price on the clouds' own pricing pages runs from about $2.46 to $11.06 per GPU-hour.
Nvidia H100: specs, memory and what it is used for
The Nvidia H100 is the Hopper-generation data-center GPU behind much of today's AI training and inference.
These pages explain how chip generations such as Nvidia H100, B200 and Rubin differ, what AMD Instinct, Google TPU, AWS Trainium, Intel Gaudi, Cerebras and Groq offer, why AI chips depend on HBM and TSMC, and what US export controls restrict, from the vendors’ own datasheets. Specs are compared in AI chips, rental prices in GPU prices, and launches in AI chip news.