| | | | | | |
| Product | Integrated Video (Included with Motherboard) | NVIDIA® L40S ADA GPU Computing Accelerator - 48GB GDDR6 - PCIe 4.0 x16 - Passive Cooling | NVIDIA® H100 NVL GPU Computing Accelerator - 94GB HBM3 - PCIe 5.0 x16 - Passive Cooling | NVIDIA® H200 NVL GPU Computing Accelerator - 141GB HBM3e - PCIe 5.0 x16 - Passive Cooling | NVIDIA® RTX 6000 Ada Generation - 48GB GDDR6 ECC - PCIe 4.0 x16 - Active Cooling (4xDP) | NVIDIA® RTX PRO 6000 Blackwell Server Edition - 96GB GDDR7 ECC - PCIe 5.0 x16 - Passive Cooling (4xDP) |
| Action | Select | Select | Select | Select | Select | Select |
| Main Specifications |
| Product Series |
| Nvidia L40S | Nvidia H100 NVL | Nvidia H200 | | |
| Core Type |
| NVIDIA TENSOR | NVIDIA TENSOR | NVIDIA TENSOR | | |
| Host Interface |
| PCI Express 4.0 x16 | PCI Express 5.0 x16 | PCI Express 5.0 x16 | PCI Express 4.0 x16 | PCI Express 5.0 x16 |
| GPU Architecture |
| Ada Lovelace | Hopper | Hopper | | |
| Product Type |
| | | | Workstation | Server |
| Product Line |
| | | | NVIDIA Professional Graphics | NVIDIA Professional Graphics |
| Memory Technology |
| | | | GDDR6 | GDDR7 |
| Memory Capacity |
| | | | 48 GB with ECC | 96 GB with ECC |
| Max Displays |
| | | | 4 Displays | 4 Displays |
| Detailed Specifications |
| Streaming Processor Cores |
| 18,176 | | | 18,176 | 24,064 CUDA Parallel Processing Cores |
| NVIDIA Tensor Cores |
| 568 | Gen 4 | | | 568 | 752 (5th Gen) |
| NVIDIA RT Cores |
| 142 | Gen 3 | | | 142 | 188 (4th Gen) |
| PCIe x16 Interconnect Bandwidth |
| | PCIe Gen5: 128GB/s | | | |
| Memory Interface |
| | | | 384-bit | 512-bit |
| Max Memory Size |
| 48GB GDDR6 with ECC | 94 GB | 141 GB | | |
| Max Memory Bandwidth |
| 864 GB/s | 7.8TB/s | 4.8TB/s | | |
| Peak FP64 |
| | 68 teraFLOPs | 30 TFLOPS | | |
| Peak FP64 Tensor Core |
| | 134 teraFLOPs | 60 TFLOPS | | |
| INT8 Tensor Core |
| 733 teraFLOPS | 7,916 TOPS | 3,341 TFLOPS | | |
| TF32 Tensor Core |
| 183 teraFLOPS | 1,979 teraFLOPs | 835 TFLOPS | | |
| FP32 |
| 91.6 teraFLOPS | 134 teraFLOPs | 60 TFLOPS | | |
| Peak BFLOAT16 Tensor Core |
| 362.05 teraFLOPS | 3,958 teraFLOPs | 1,671 TFLOPS | | |
| Peak FP16 Tensor Core |
| 362.05 teraFLOPS | 3,958 teraFLOPs | 1,671 TFLOPS | | |
| Peak FP8 Tensor Core |
| 733 teraFLOPS | 7,916 teraFLOPs | 3,341 TFLOPS | | |
| Peak INT4 Tensor Core |
| 733 teraFLOPS | | | | |
| Total NVLink Bandwidth |
| Not supported | 600GB/s | | | |
| Multi-Instance GPUs |
| No | | | | |
| Tensor Performance |
| | | | 1457.0 TFLOPS | |
| NVENC | NVDEC |
| 3x l 3x (includes AV1 encode and decode) | | | | |
| Secure Boot with Root of Trust |
| Yes | | | | |
| NEBS Ready |
| Level 3 | | | | |
| Transistor Count |
| | | | 76.3 billion | |
| DisplayPort Connectors |
| 4x DisplayPort 1.4a | | | | |
| Cooling |
| Passive | Passive | Passive | | |
| Dual Slot |
| | Yes | | | |
| Dimensions |
| 4.4" (H) x 10.5" (L) | | | 4.4" H x 10.5" L | 4.4” H x 10.5” L, FHFL Dual Slot |
| Form Factor |
| | PCIe | Dual-slot air-cooled | | |
| Lithography |
| | | | 4 nm NVIDIA Custom Process | 4N NVIDIA Custom Process |
| Supplementary Power Connectors |
| 1x 16-pin | | | 1x PCIe CEM5 16-pin | 1x PCIe CEM5 16-pin |
| Max Graphics Card Power (W) |
| 350W | 400W | Up to 600W (configurable) | 300W | 400 W – 600 W (configurable) |
| Processor |
| | | | NVIDIA Ada Lovelace | NVIDIA Blackwell Architecture |
| Memory Bandwidth |
| | | | 960 GB/s | Up to 1.6 TB/s |
| Peak Single Precision FP32 Performance |
| | | | 91.1 TFLOPS | |
| RT Core Performance |
| | | | 210.6 TFLOPS | |
| DisplayPort Output |
| | | | 4x DP 1.4a | |
| Minimum Recommended Power, Single Card (W) |
| | | | 600 | 800 |
| Minimum Recommended Power, 2-Way (W) |
| | | | 750 | 1600 |
| Minimum Recommended Power, 3-Way (W) |
| | | | 850 | 2000 |
| Minimum Recommended Power, 4-Way (W) |
| | | | 1000 | 2400 |
| Thermal Solution |
| | | | Blower Active Fan | Passive |
| Slot Height |
| | | | 2-Slot | 2-Slot |
| Action | Select | Select | Select | Select | Select | Select |