Product	AMD Instinct™ MI210 Accelerator - 64GB HBM2e - PCIe 4.0 x16 - Passive Cooling	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 NVL GPU Computing Accelerator - 94GB HBM3 - PCIe 5.0 x16 - Passive Cooling	NVIDIA® RTX 6000 Ada Generation - 48GB GDDR6 ECC - PCIe 4.0 x16 - Active Cooling (4xDP)
Action	Select	Select	Select	Select	Select
Main Specifications
Product Series	AMD Instinct	Nvidia L40	Nvidia L40S	Nvidia H100 NVL
Core Type		NVIDIA TENSOR	NVIDIA TENSOR	NVIDIA TENSOR
Core Clock Speed	1700 MHz
Host Interface	PCI Express 4.0 x16	PCI Express 4.0 x16	PCI Express 4.0 x16	PCI Express 5.0 x16	PCI Express 4.0 x16
GPU Architecture	CDNA2	Ada Lovelace	Ada Lovelace	Hopper
Product Type					Workstation
Product Line					NVIDIA Professional Graphics
Memory Technology					GDDR6
Memory Capacity					48 GB with ECC
Max Displays					4 Displays
Detailed Specifications
Streaming Processor Cores	6656		18,176		18,176
Compute Units	104
NVIDIA Tensor Cores			568 | Gen 4		568
NVIDIA RT Cores			142 | Gen 3		142
PCIe x16 Interconnect Bandwidth				PCIe Gen5: 128GB/s
Memory Clock Speed	1.6 GHz
Memory Interface	4096-bit				384-bit
Max Memory Size	64 GB HBM2e	48 GB GDDR6 with ECC	48GB GDDR6 with ECC	94 GB
Max Memory Bandwidth	Up to 1638.4 GB/s		864 GB/s	7.8TB/s
Infinity Fabric™ Links	3
Peak Infinity Fabric™ Link Bandwidth	100 GB/s
Peak FP64				68 teraFLOPs
Peak FP64 Tensor Core				134 teraFLOPs
Peak FP32	22.6 TFLOPs		91.6 teraFLOPS	134 teraFLOPs
Peak TF32 Tensor Core			183 teraFLOPS	1,979 teraFLOPs
Peak BFLOAT16 Tensor Core			362.05 teraFLOPS	3,958 teraFLOPs
Peak FP16 Tensor Core			362.05 teraFLOPS	3,958 teraFLOPs
Peak FP8 Tensor Core			733 teraFLOPS	7,916 teraFLOPs
Peak INT8 Tensor Core			733 teraFLOPS	7,916 TOPS
Peak INT4 Tensor Core			733 teraFLOPS
NVIDIA NVLink™ Interconnect Bandwidth			Not supported	600GB/s
Multi-Instance GPUs			No
Tensor Performance					1457.0 TFLOPS
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
Peak Single Precision Matrix (FP32) Performance	45.3 TFLOPs
Peak Double Precision Matrix (FP64) Performance	45.3 TFLOPs
Peak Double Precision (FP64) Performance	22.6 TFLOPs
Peak INT4 Performance	181 TOPs
Peak bfloat16	181 TFLOPs
ECC Protection	Yes (Full-Chip)
Transistor Count					76.3 billion
DisplayPort Connectors		4x DP 1.4a	4x DisplayPort 1.4a
OS Support	Linux x86_64
Cooling	Passive	Passive	Passive	Passive
Dual Slot	yes	Yes		Yes
Dimensions	10.5" (267 mm) Board Length	4.4" (H) x 10.5" (L)	4.4" (H) x 10.5" (L)		4.4" H x 10.5" L
Form Factor	Full Height	PCIe		PCIe
Lithography					4 nm NVIDIA Custom Process
Supplementary Power Connectors	1x8 pin 12V EPS	1x 16-pin PCIe CEM5	1x 16-pin		1x PCIe CEM5 16-pin
Max Graphics Card Power (W)	300W Peak	300W	350W	400W	300W
Processor					NVIDIA Ada Lovelace
Memory Bandwidth					960 GB/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
Minimum Recommended Power, 2-Way (W)					750
Minimum Recommended Power, 3-Way (W)					850
Minimum Recommended Power, 4-Way (W)					1000
Thermal Solution					Blower Active Fan
Slot Height					2-Slot
Action	Select	Select	Select	Select	Select