H200 GPU
Next-Gen AI·HPC Accelerator
Maximizing AI and HPC workload performance

Maximizing AI and HPC workload performance
| Form Factor | H200 SXM¹ | H200 NVL¹ |
|---|---|---|
| FP64 | 34 teraFLOPS | 34 teraFLOPS |
| FP64 Tensor Core | 67 teraFLOPS | 67 teraFLOPS |
| FP32 | 67 teraFLOPS | 67 teraFLOPS |
| TF32 Tensor Core | 989 teraFLOPS² | 989 teraFLOPS² |
| BFLOAT16 Tensor Core | 1,979 teraFLOPS² | 1,979 teraFLOPS² |
| FP16 Tensor Core | 1,979 teraFLOPS² | 1,979 teraFLOPS² |
| FP8 Tensor Core | 3,958 teraFLOPS² | 3,958 teraFLOPS² |
| INT8 Tensor Core | 3,958 TOPS² | 3,958 TOPS² |
| GPU memory | 141GB | 141GB |
| GPU memory bandwidth | 4.8TB/s | 4.8TB/s |
| Decoders | 7 NVDEC 7 JPEG | 7 NVDEC 7 JPEG |
| Max thermal design power (TDP) | Up to 700W (configurable) | Up to 600W (configurable) |
| Multi-Instance GPUs | Up to 7 MIGS @ 18GB each | Up to 7 MIGS @ 18GB each |
| Form factor | SXM | PCIe |
| Interconnect | NVLink: 900GB/s PCIe Gen5: 128GB/s | 2-way or 4-way NVIDIA NVLink Bridge: 900GB/s PCIe Gen5: 128GB/s |
| Server options |
4 or 8 GPUs NVIDIA HGX H100 Partner and NVIDIA-Certified System™ |
8 GPUs NVIDIA MGX™ H200 NVL Partner and NVIDIA-Certified Systems |
| NVIDIA AI Enterprise | Add-on | Included |