Product	NVIDIA® L4 ADA GPU Computing Accelerator - 24GB GDDR6X - PCIe 4.0 x16 - Passive Cooling	NVIDIA® L40S ADA GPU Computing Accelerator - 48GB GDDR6 - PCIe 4.0 x16 - Passive Cooling	NVIDIA® RTX PRO 4000 Blackwell - 24GB GDDR7 ECC - PCIe 5.0 x16 - Active Cooling (4xDP)	NVIDIA® RTX PRO 4500 Blackwell - 32GB GDDR7 ECC - PCIe 5.0 x16 - Active Cooling (4xDP)	NVIDIA® RTX PRO 4500 Blackwell Server Edition - 32GB GDDR7 ECC - PCIe 5.0 x16 - Passive Cooling	NVIDIA® RTX PRO 5000 Blackwell - 48GB GDDR7 ECC - PCIe 5.0 x16 - Active Cooling (4xDP)
Action	Select	Select	Select	Select	Select	Select
Main Specifications
Product Series	Nvidia L4	Nvidia L40S
Core Type	NVIDIA TENSOR	NVIDIA TENSOR
Core Clock Speed	795 MHz Base | 2040 MHz Boost
Host Interface	PCI Express 4.0 x16	PCI Express 4.0 x16	PCI Express 5.0 x16	PCI Express 5.0 x16	PCI Express 5.0 x16	PCI Express 5.0 x16
GPU Architecture	Ada Lovelace	Ada Lovelace
Product Type			Workstation	Workstation	Server	Workstation
Product Line			NVIDIA Professional Graphics	NVIDIA Professional Graphics	NVIDIA Professional Graphics	NVIDIA Professional Graphics
Memory Technology			GDDR7	GDDR7	GDDR7	GDDR7
Memory Capacity			24 GB with ECC	32 GB with ECC	32 GB	48 GB with ECC
Max Displays			4 Displays	4 Displays		4 Displays
Detailed Specifications
Streaming Processor Cores		18,176	8960 CUDA Parallel Processing Cores	10,496 CUDA Parallel Processing Cores	10,496 CUDA Parallel Processing Cores	14,080 CUDA Parallel Processing Cores
NVIDIA Tensor Cores		568 | Gen 4	280	328	203 (5th Gen)	440
NVIDIA RT Cores		142 | Gen 3	70	82	82 (4th Gen)	110
Memory Clock Speed	6251 MHz
Memory Interface	192-bit		192-bit	256-bit	256-bit	384-bit
Max Memory Size	24 GB	48GB GDDR6 with ECC
Max Memory Bandwidth	300 GB/s	864 GB/s
ECC Protection	On by Default
INT8 Tensor Core	485 TOPS | Sparsity	733 teraFLOPS
TF32 Tensor Core	120 TFLOPS | Sparsity	183 teraFLOPS
FP32	30.3 TFLOPS	91.6 teraFLOPS
Peak BFLOAT16 Tensor Core	242 TFLOPS | Sparsity	362.05 teraFLOPS
Peak FP16 Tensor Core	242 TFLOPS | Sparsity	362.05 teraFLOPS
Peak FP8 Tensor Core	485 TFLOPS | Sparsity	733 teraFLOPS
Peak INT4 Tensor Core		733 teraFLOPS
Total NVLink Bandwidth		Not supported
Multi-Instance GPUs		No
NVENC | NVDEC	2 | 4 | 4 | JPEG Decoders | AV1 Encode and Decode	3x l 3x (includes AV1 encode and decode)
Secure Boot with Root of Trust	Yes	Yes
NEBS Ready	Yes | Level 3	Level 3
Transistor Count				45.6 Billion	45.6 Billion	92.2 Billion
DisplayPort Connectors	None | vGPU Only	4x DisplayPort 1.4a
Cooling	Passive	Passive
Dual Slot	No
Dimensions		4.4" (H) x 10.5" (L)	4.4" H x 9.5" L, single height	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	6.61” L x 2.71” H (Low-profile)
Lithography				4N NVIDIA Custom Process	4 nm Custom Process	4N NVIDIA Custom Process
Supplementary Power Connectors		1x 16-pin	1x PCIe CEM5 16-pin	1x PCIe CEM5 16-pin	1x PCIe CEM5 16-pin	1x PCIe CEM5 16-pin
Max Graphics Card Power (W)	72W	350W	140W	200W	165W	300W
Processor			NVIDIA Blackwell Architecture	NVIDIA Blackwell Architecture	NVIDIA Blackwell Architecture	NVIDIA Blackwell Architecture
Memory Bandwidth			672 GB/s	896 GB/s	800 GB/s	1344 GB/s
Peak Single Precision FP32 Performance					51 TFLOPS
DisplayPort Output			4x DP 2.1	4x DP 2.1		4x DP 2.1
Minimum Recommended Power, Single Card (W)			550	550		600
Minimum Recommended Power, 2-Way (W)			750	750		750
Minimum Recommended Power, 3-Way (W)			850	850		850
Minimum Recommended Power, 4-Way (W)			1000	1000		1000
Thermal Solution			Blower Active Fan	Blower Active Fan	Passive	Blower Active Fan
Slot Height			1-Slot	2-Slot	Single Slot	2-Slot
Action	Select	Select	Select	Select	Select	Select