NVIDIA H200 Tensor Core GPU

Supercharging AI and HPC workloads

The GPU for Generative AI and HPC

The NVIDIA H200 Tensor Core GPU supercharges generative AI and high-performance computing (HPC) workloads with game-changing performance and memory capabilities. As the first GPU with HBM3e, the H200’s larger and faster memory fuels the acceleration of generative AI and large language models (LLMs) while advancing scientific computing for HPC workloads.

• Higher memory capacity

  The H200 comes with 141 GB of HBM3e memory, almost twice the capacity of the H100.

• Increase memory bandwidth

  The H200 has 4.8 TB/s of memory bandwidth, providing 1.4 times more bandwidth than the H100, enabling faster data processing

• Enhanced AI performance

  The H200 is optimized for generative AI and large language models (LLM) to enable faster and more efficient AI model training and inference.