Data center · PCIe
NVIDIA H200 NVL PCIe 141 GB
A Hopper PCIe accelerator with 141 GB of HBM3e for AI and HPC servers. The NVL variant supports two- or four-GPU NVLink bridge configurations and is distinct from H200 SXM.
Technical specifications
| Architecture | NVIDIA Hopper |
|---|---|
| GPU memory | 141 GB HBM3e |
| Memory bandwidth | 4.8 TB/s |
| Form factor | PCIe, dual-slot, air-cooled |
| Host interface | PCIe Gen5 |
| NVLink bandwidth per GPU | 900 GB/s; 2- or 4-way bridge |
| Maximum TDP | Up to 600 W, configurable |
| MIG | Up to 7 instances |
Applications
- LLM and other neural-network inference.
- Training and fine-tuning neural networks.
- Scientific simulations and GPU-accelerated data analysis.
Compatibility
- Verify the exact server model, slot clearance, power cabling and cooling with the OEM. A PCIe slot alone does not establish compatibility. Passive cooling requires forced airflow from the server.
- 141 GB refers to one GPU, not an NVLink group. The bridge, card spacing and server support must match the intended two- or four-GPU configuration. NVIDIA marks this specification table as preliminary and subject to change.
- 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.
- 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.