The NVIDIA® H100, powered by the new Hopper architecture, is a flagship GPU offering powerful AI acceleration, big data processing, and high-performance computing (HPC). With 80 GB of HBM2e high-speed memory, this GPU can handle tasks related to language models or AI with ease.
With H100 SXM you get:
Frees you from node capacity planning and enables on-demand application scaling.
Deliver resources with custom specifications in seconds. Frees you from node management and allows you to focus on application development.
Only pay when your instance is running, and there are no hidden fees like data egress or ingress.
Form Factor | H100 SXM | H100 PCle |
---|---|---|
GPU memory | 80 GB | 80 GB |
GPU memory bandwidth | 3.35 TB/s | 2 TB/s |
Max thermal design Power (TDP) | Up to 700W (configurable) | 300-350W (configurable) |
Multi-instance GPUs | Up to 7 MIGS @ 10 GB each | |
Form factor | SXM | PCle
Dual-slot air-cooled |
interconnect | NVLink: 900GB/s PCle Gen5 128GB/s |
NVLink: 600GB/s
PCle Gen5: 128GB/s |