Product	NVIDIA® L4 ADA GPU Computing Accelerator - 24GB GDDR6X - PCIe 4.0 x16 - Passive Cooling	NVIDIA® RTX A400 - 4GB GDDR6 - PCIe 4.0 x8 - Active Cooling (4x mDP)	NVIDIA® RTX 2000 Ada Generation - 16GB GDDR6 ECC - PCIe 4.0 x8 - Active Cooling (4x mDP)	NVIDIA® RTX PRO 4500 Blackwell - 32GB GDDR7 ECC - PCIe 5.0 x16 - Active Cooling (4xDP)	NVIDIA® RTX PRO 5000 Blackwell - 48GB GDDR7 ECC - PCIe 5.0 x16 - Active Cooling (4xDP)	NVIDIA® RTX PRO 6000 Blackwell Max-Q Workstation Edition - 96GB GDDR7 ECC - PCIe 5.0 x16 - Active Cooling (4xDP)
Action	Select	Select	Select	Select	Select	Select
Main Specifications
Product Series	Nvidia L4
Core Type	NVIDIA TENSOR
Core Clock Speed	795 MHz Base | 2040 MHz Boost
Host Interface	PCI Express 4.0 x16	PCI Express 4.0 x8	PCI Express 4.0 x8	PCI Express 5.0 x16	PCI Express 5.0 x16	PCI Express 5.0 x16
GPU Architecture	Ada Lovelace
Product Type		Workstation	Workstation	Workstation	Workstation	Workstation
Product Line		NVIDIA Professional Graphics	NVIDIA Professional Graphics	NVIDIA Professional Graphics	NVIDIA Professional Graphics	NVIDIA Professional Graphics
Memory Technology		GDDR6	GDDR6 with ECC	GDDR7	GDDR7	GDDR7
Memory Capacity		4 GB	16 GB	32 GB with ECC	48 GB with ECC	96 GB with ECC
Max Displays		4 Displays		4 Displays	4 Displays	4 Displays
Detailed Specifications
Streaming Processor Cores		768 CUDA Cores	2816 CUDA Cores	10,496 CUDA Parallel Processing Cores	14,080 CUDA Parallel Processing Cores	24,064 CUDA Parallel Processing Cores
NVIDIA Tensor Cores		24	88	328	440	752
NVIDIA RT Cores		6	22	82	110	188
Memory Clock Speed	6251 MHz
Memory Interface	192-bit	64-bit	128-bit	256-bit	384-bit	512-bit
Max Memory Size	24 GB
Max Memory Bandwidth	300 GB/s
ECC Protection	On by Default
INT8 Tensor Core	485 TOPS | Sparsity
TF32 Tensor Core	120 TFLOPS | Sparsity
FP32	30.3 TFLOPS
Peak BFLOAT16 Tensor Core	242 TFLOPS | Sparsity
Peak FP16 Tensor Core	242 TFLOPS | Sparsity
Peak FP8 Tensor Core	485 TFLOPS | Sparsity
Tensor Performance		21.7 TFLOPS	191.9 TFLOPS
NVENC | NVDEC	2 | 4 | 4 | JPEG Decoders | AV1 Encode and Decode
Secure Boot with Root of Trust	Yes
NEBS Ready	Yes | Level 3
Transistor Count		8.7 Billion	19.9 Billion	45.6 Billion	92.2 Billion	92.2 Billion
DisplayPort Connectors	None | vGPU Only
Cooling	Passive
Dual Slot	No
Dimensions		2.7" H x 6.4" L	2.7” H x 6.6”	4.4" H x 10.5" L	4.4” H x 10.5” L, FHFL Dual Slot	4.4” H x 10.5” L, FHFL Dual Slot
Form Factor	6.61” L x 2.71” H (Low-profile)
Lithography		8N | NVIDIA Custom Process	4N NVIDIA Custom Process	4N NVIDIA Custom Process	4N NVIDIA Custom Process	4N NVIDIA Custom Process
Supplementary Power Connectors				1x PCIe CEM5 16-pin	1x PCIe CEM5 16-pin	1x PCIe CEM5 16-pin
Max Graphics Card Power (W)	72W	50W	70W	200W	300W	300W
Processor		Ampere	NVIDIA Ada Lovelace (AD107)	NVIDIA Blackwell Architecture	NVIDIA Blackwell Architecture	NVIDIA Blackwell Architecture
Memory Bandwidth		96 GB/sec	224 GB/sec	896 GB/s	1344 GB/s	1792 GB/s
Peak Single-Precision Performance			12 TFLOPS
Graphics Resolution		Support up to four 5K monitors @ 60Hz per card	7680 x 4320 x36 bpp at 60 Hz
Peak Single Precision FP32 Performance		2.7 TFLOPS
Multi-GPU Scalability			Not Supported
NVLink Interconnect		Not Supported
RT Core Performance		5.3 TFLOPS	27.7 TFLOPS
DisplayPort Output			4x Mini DisplayPort 1.4a	4x DP 2.1	4x DP 2.1	4x DP 2.1
Mini DisplayPort Output		4x mDisplayPort 1.4a
Minimum Recommended Power, Single Card (W)				550	600	600
Minimum Recommended Power, 2-Way (W)				750	750	900
Minimum Recommended Power, 3-Way (W)				850	850	1200
Minimum Recommended Power, 4-Way (W)				1000	1000	1600
Thermal Solution		Active Fan	Blower Active Fan	Blower Active Fan	Blower Active Fan	Blower Active Fan
Slot Height		Single Slot	Dual Slot	2-Slot	2-Slot	2-Slot
Action	Select	Select	Select	Select	Select	Select