Product	NVIDIA® L4 ADA GPU Computing Accelerator - 24GB GDDR6X - PCIe 4.0 x16 - Passive Cooling	NVIDIA® RTX 2000 Ada Generation - 16GB GDDR6 ECC - PCIe 4.0 x8 - Active Cooling (4x mDP)
Action	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
GPU Architecture	Ada Lovelace
Product Type		Workstation
Product Line		NVIDIA Professional Graphics
Memory Technology		GDDR6 with ECC
Memory Capacity		16 GB
Detailed Specifications
Streaming Processor Cores		2816 CUDA Cores
NVIDIA Tensor Cores		88
NVIDIA RT Cores		22
Memory Clock Speed	6251 MHz
Memory Interface	192-bit	128-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		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		19.9 Billion
DisplayPort Connectors	None | vGPU Only
Cooling	Passive
Dual Slot	No
Dimensions		2.7” H x 6.6”
Form Factor	6.61” L x 2.71” H (Low-profile)
Lithography		4N NVIDIA Custom Process
Max Graphics Card Power (W)	72W	70W
Processor		NVIDIA Ada Lovelace (AD107)
Memory Bandwidth		224 GB/sec
Peak Single-Precision Performance		12 TFLOPS
Graphics Resolution		7680 x 4320 x36 bpp at 60 Hz
Multi-GPU Scalability		Not Supported
RT Core Performance		27.7 TFLOPS
DisplayPort Output		4x Mini DisplayPort 1.4a
Thermal Solution		Blower Active Fan
Slot Height		Dual Slot
Action	Select	Select