ProductNVIDIA® L40S ADA GPU Computing Accelerator - 48GB GDDR6 - PCIe 4.0 x16 - Passive CoolingNVIDIA® H200 NVL GPU Computing Accelerator - 141GB HBM3e - PCIe 5.0 x16 - Passive Cooling
ActionSelectSelect
Main Specifications
Product Series Nvidia L40SNvidia H200
Core Type NVIDIA TENSORNVIDIA TENSOR
Host Interface PCI Express 4.0 x16PCI Express 5.0 x16
GPU Architecture Ada LovelaceHopper
Detailed Specifications
Streaming Processor Cores 18,176
NVIDIA Tensor Cores 568 | Gen 4
NVIDIA RT Cores 142 | Gen 3
Max Memory Size 48GB GDDR6 with ECC141 GB
Max Memory Bandwidth 864 GB/s4.8TB/s
Peak FP64 30 TFLOPS
Peak FP64 Tensor Core 60 TFLOPS
INT8 Tensor Core 733 teraFLOPS3,341 TFLOPS
TF32 Tensor Core 183 teraFLOPS835 TFLOPS
FP32 91.6 teraFLOPS60 TFLOPS
Peak BFLOAT16 Tensor Core 362.05 teraFLOPS1,671 TFLOPS
Peak FP16 Tensor Core 362.05 teraFLOPS1,671 TFLOPS
Peak FP8 Tensor Core 733 teraFLOPS3,341 TFLOPS
Peak INT4 Tensor Core 733 teraFLOPS
Total NVLink Bandwidth Not supported
Multi-Instance GPUs No
NVENC | NVDEC 3x l 3x (includes AV1 encode and decode)
Secure Boot with Root of Trust Yes
NEBS Ready Level 3
DisplayPort Connectors 4x DisplayPort 1.4a
Cooling PassivePassive
Dimensions 4.4" (H) x 10.5" (L)
Form Factor Dual-slot air-cooled
Supplementary Power Connectors 1x 16-pin
Max Graphics Card Power (W) 350WUp to 600W (configurable)
ActionSelectSelect