Nvidia unveils HGX H200 AI computing platform
Published in Graphics


Featuring the NVIDIA H200 GPU with 141GB of HBM3e memory

At the SC23 conference in Denver, Colorado, Nvidia unveiled the HGX H200, the world's leading AI computing platform, according to the company. Based on Nvidia Hopper architecture and featuring the Nvidia H200 GPU, it promises a significant performance boost to generative AI, large language models, and HPC workloads.