NVIDIA
NVIDIA H200
NVIDIA Hopper-architecture data-center GPU with HBM3e memory, positioned for memory-bound large-language-model inference and training.
Pre-orderRequest a quote →
The H200 extends the Hopper generation with HBM3e memory, increasing memory capacity and bandwidth relative to the H100 for large-model workloads. Available in SXM and other server configurations. Request a quote for current availability.
Specifications
| Architecture | NVIDIA Hopper |
|---|---|
| Memory | HBM3e |
| Interconnect | NVLink |
Specifications shown are headline figures. Confirm full configuration details when you request a quote.
Last updated
Request a quote for NVIDIA H200
Tell us your requirements and we'll get back to you with availability and pricing.
or reach us directly at