Product	NVIDIA® L40 ADA GPU Computing Accelerator - 48GB GDDR6 - PCIe 4.0 x16 - Passive Cooling	NVIDIA® L40S ADA GPU Computing Accelerator - 48GB GDDR6 - PCIe 4.0 x16 - Passive Cooling	NVIDIA® H100 GPU Computing Accelerator - 80GB HBM2e - PCIe 5.0 x16 - Passive Cooling (w/o CEC)
Action	Select	Select	Select
Main Specifications
Product Series	Nvidia L40	Nvidia L40S	Nvidia H100
Core Type	NVIDIA TENSOR	NVIDIA TENSOR	NVIDIA TENSOR
Host Interface	PCI Express 4.0 x16	PCI Express 4.0 x16	PCI Express 5.0 x16
GPU Architecture	Ada Lovelace	Ada Lovelace	Hopper
Detailed Specifications
Streaming Processor Cores		18,176
NVIDIA Tensor Cores		568 | Gen 4
NVIDIA RT Cores		142 | Gen 3
PCIe x16 Interconnect Bandwidth			PCIe Gen5: 128GB/s
Max Memory Size	48 GB GDDR6 with ECC	48GB GDDR6 with ECC	80 GB
Max Memory Bandwidth		864 GB/s	2.0TB/s
Peak FP64			24 teraFLOPS
Peak FP64 Tensor Core			48 teraFLOPS
INT8 Tensor Core		733 teraFLOPS	3,200 TOPS
TF32 Tensor Core		183 teraFLOPS	800 teraFLOPS
FP32		91.6 teraFLOPS	48 teraFLOPS
Peak BFLOAT16 Tensor Core		362.05 teraFLOPS	1,600 teraFLOPS
Peak FP16 Tensor Core		362.05 teraFLOPS	1,600 teraFLOPS
Peak FP8 Tensor Core		733 teraFLOPS	3,200 teraFLOPS
Peak INT4 Tensor Core		733 teraFLOPS
Total NVLink Bandwidth		Not supported	600GB/s
Multi-Instance GPUs		No	Up to 7 MIGS @ 10GB each
vGPU Software Support	NVIDIA vPC/vApps, NVIDIA RTX Virtual Workstation (vWS)
NVENC | NVDEC	3x | 3x (Includes AV1 Encode & Decode)	3x l 3x (includes AV1 encode and decode)
Secure Boot with Root of Trust	Yes	Yes
NEBS Ready	Yes / Level 3	Level 3
DisplayPort Connectors	4x DP 1.4a	4x DisplayPort 1.4a
Cooling	Passive	Passive	Passive
Dual Slot	Yes		Yes
Dimensions	4.4" (H) x 10.5" (L)	4.4" (H) x 10.5" (L)
Form Factor	PCIe		PCIe
Supplementary Power Connectors	1x 16-pin PCIe CEM5	1x 16-pin	1x 16-pin PCIe CEM5
Max Graphics Card Power (W)	300W	350W	350W
Action	Select	Select	Select