Özer Cem KELAHMETKELAHMET
Glossary · MLOps and AI infrastructure

What is NVIDIA B200? Definition and meaning

A GPU with a new architecture, larger memory and support for lower-precision formats.

Definition

NVIDIA B200: A GPU with a new architecture, larger memory and support for lower-precision formats.

In short: Blackwell-generation datacenter GPU.

When it is used

The newest generation of training and inference.

Where it fits

NVIDIA B200 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 H200: A Hopper GPU with 141 GB of HBM3e memory.

Learn more

The full guide to NVIDIA B200 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: Norse · Next term: NVIDIA H100

Last updated Nov 18, 2026
Type to search.
    ↑↓ navigate↵ open