Specs
Quick Specs
- Architecture: Hopper GPU with Transformer Engine
- CUDA Cores: 16,896
- Tensor Cores: 528 Fourth Generation
- FP8 Performance: 3959 TFLOPS (with sparsity)
- FP16/BF16 Performance: 1979 TFLOPS (with sparsity)
- TF32 Performance: 989 TFLOPS (with sparsity)
- FP64 Performance: 30 TFLOPS
- Memory: 141 GB HBM3
- Memory Bandwidth: 4.8 TB/s
- NVLink: 900 GB/s (18 links, 50 GB/s each)
- TDP: Up to 600W (configurable)
- Form Factor: Dual-slot PCIe
Part Number:
- N/A
Compatible With:
- Dell R770
(Click to View)
Base Standard Capabilities
| Technical Specifications | ||
|---|---|---|
| H200 SXM | H200 NVL | |
| FP64 | 34 TFLOPS | 30 TFLOPS |
| FP64 Tensor Core | 67 TFLOPS | 60 TFLOPS |
| FP32 | 67 TFLOPS | 60 TFLOPS |
| TF32 Tensor Core² | 989 TFLOPS | 835 TFLOPS |
| BFLOAT16 Tensor Core³ | 1,979 TFLOPS | 1,671 TFLOPS |
| FP16 Tensor Core² | 1,979 TFLOPS | 1,671 TFLOPS |
| FP8 Tensor Core⁴ | 3,958 TFLOPS | 3,341 TFLOPS |
| INT8 Tensor Core² | 3,958 TFLOPS | 3,341 TFLOPS |
| GPU Memory Bandwidth | 4.8TB/s | 4.8TB/s |
| Decoders | 7 NVDEC | 7 NVDEC |
| 7 JPEG | 7 JPEG | |
| Confidential Computing | Supported | Supported |
| Max Thermal Design Power (TDP) | Up to 700W (configurable) | Up to 600W (configurable) |
| Multi-Instance GPUs | Up to 7 MIGs @ 16GB each | Up to 7 MIGs @ 16.5GB each |
| Form Factor | SXM | PCIe |
| Interconnect | NVLink: 900GB/s | Dual-slot air-cooled |
| PCIe Gen5: 128GB/s | 2- or 4-way NVIDIA NVLink bridge: 900GB/s per GPU | |
| PCIe Gen5: 128GB/s | ||
| Server Options | NVLink: 900GB/s | NVLink: 900GB/s |
| PCIe Gen5: 128GB/s | PCIe Gen5: 128GB/s | |
| NVLink: 900GB/s | NVLink: 900GB/s | |
| PCIe Gen5: 128GB/s | PCIe Gen5: 128GB/s | |
| NVidia HGX H200 partner and NVIDIA- Certified Systems* with 4 or 8 GPUs | NVidia MGX* H200 NVL partner and NVIDIA- Certified Systems with up to 8 GPUs | |
| NVIDIA AI Enterprise | Add-on | Included |