Glossary · MLOps and AI infrastructure
What is NVIDIA H200? Definition and meaning
A Hopper GPU with 141 GB of HBM3e memory.
Definition
NVIDIA H200: A Hopper GPU with 141 GB of HBM3e memory.
In short: H100 with more and faster memory.
When it is used
Memory-bound inference and large-model workloads.
Where it fits
NVIDIA H200 belongs to Hardware in the MLOps and AI infrastructure topic. These are the other terms in the same group:
- CUDA: A programming model and toolkit for running general-purpose code on NVIDIA GPUs.
- NCCL: A library that implements fast all-reduce and other communication between GPUs.
- Cloud TPU: Google's custom accelerators for machine-learning workloads.
- NVIDIA H100: A GPU with Transformer Engine and fast interconnect, widely used for training and inference.
- NVIDIA B200: A GPU with a new architecture, larger memory and support for lower-precision formats.
Learn more
The full guide to NVIDIA H200 explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.
Previous term: NVIDIA H100 · Next term: OAuth 2.0