Data center · 8-GPU platform
NVIDIA HGX H200 8-GPU
An eight-GPU Hopper platform using H200 SXM modules with HBM3e memory. It targets AI training, inference and memory-intensive scientific workloads in an integrated server.
Platform, not a single card
Technical specifications
| Architecture | NVIDIA Hopper |
|---|---|
| Platform configuration | 8 x H200 SXM |
| Memory per GPU | 141 GB HBM3e |
| Memory bandwidth per GPU | 4.8 TB/s |
| NVLink bandwidth per GPU | 900 GB/s |
| Maximum TDP per GPU | Up to 700 W, configurable |
Applications
- Training and fine-tuning neural networks.
- LLM and other neural-network inference.
- Scientific simulations and GPU-accelerated data analysis.
Compatibility
- HGX is a GPU baseboard platform, not a PCIe card or a complete server. CPU, system RAM, networking, chassis, power and cooling depend on the OEM server configuration. Confirm the complete bill of materials with the system vendor.
- Memory belongs to individual GPUs. NVLink does not automatically turn it into one GPU's local memory; using multiple GPUs requires software that distributes the model or workload.
- The memory, bandwidth and TDP rows are per H200 SXM, not totals for the platform. GPU TDP is not the complete server's power consumption. NVIDIA marks the H200 specification table as preliminary and subject to change.
- Check driver, CUDA/framework and operating-system support for the intended workload. Virtualization and enterprise software may require separate licenses and a supported host configuration.
Manufacturer sources
Specifications checked against the listed NVIDIA sources: .
Request a quote
Each quote is prepared individually for the selected variant, quantity and destination. The RFQ covers condition, configuration, source, warranty, availability and delivery timing.