Product	NVIDIA® A30 GPU Computing Accelerator - 24GB HBM2 - PCIe 4.0 x16 - Passive Cooler	NVIDIA® L4 ADA GPU Computing Accelerator - 24GB GDDR6X - PCIe 4.0 x16 - Passive Cooling	NVIDIA® L40 ADA GPU Computing Accelerator - 48GB GDDR6 - PCIe 4.0 x16 - Passive Cooling	NVIDIA® T1000 8GB GDDR6 - PCIe 3.0 x16 - Active Cooling (4x mDP)
Action	Select	Select	Select	Select
Main Specifications
Product Series	Nvidia A30	Nvidia L4	Nvidia L40
Core Type	NVIDIA TENSOR	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 4.0 x16	PCI Express 3.0 x16
GPU Architecture	Ampere	Ada Lovelace	Ada Lovelace
Product Type				Workstation
Memory Technology				GDDR6
Memory Capacity				8 GB
Max Displays				4 Displays
Detailed Specifications
Streaming Processor Cores				896 CUDA Parallel-Processing Cores
Memory Clock Speed		6251 MHz
Memory Interface		192-bit		128-bit
Max Memory Size	24 GB HBM2	24 GB	48 GB GDDR6 with ECC
Max Memory Bandwidth	933 GB/s	300 GB/s
ECC Protection		On by Default
Peak FP64	5.2 teraFLOPS
Peak FP64 Tensor Core	10.3 teraFLOPS
INT8 Tensor Core	330 TOPS | 661 TOPS	485 TOPS | Sparsity
TF32 Tensor Core	82 teraFLOPS | 165 teraFLOPS	120 TFLOPS | Sparsity
FP32	10.3 teraFLOPS	30.3 TFLOPS
Peak BFLOAT16 Tensor Core	165 teraFLOPS | 330 teraFLOPS	242 TFLOPS | Sparsity
Peak FP16 Tensor Core	165 teraFLOPS | 330 teraFLOPS	242 TFLOPS | Sparsity
Peak FP8 Tensor Core		485 TFLOPS | Sparsity
Peak INT4 Tensor Core	661 TOPS | 1321 TOPS
Total NVLink Bandwidth	Third-gen NVLINK: 200GB/s
vGPU Software Support			NVIDIA vPC/vApps, NVIDIA RTX Virtual Workstation (vWS)
NVENC | NVDEC		2 | 4 | 4 | JPEG Decoders | AV1 Encode and Decode	3x | 3x (Includes AV1 Encode & Decode)
Secure Boot with Root of Trust		Yes	Yes
NEBS Ready		Yes | Level 3	Yes / Level 3
DisplayPort Connectors		None | vGPU Only	4x DP 1.4a
Cooling		Passive	Passive
Dual Slot	Dual-slot	No	Yes
Dimensions			4.4" (H) x 10.5" (L)	2.713” H x 6.137” L
Form Factor		6.61” L x 2.71” H (Low-profile)	PCIe
Supplementary Power Connectors	1x 8-pin CPU (EPS12V)		1x 16-pin PCIe CEM5
Max Graphics Card Power (W)	165W	72W	300W	50W
Processor				NVIDIA Turing
Memory Bandwidth				160 GB/s
API Support				CUDA C, CUDA C++, DirectCompute 5.0, OpenCL, Java, Python, and Fortran Shader Model 5.1 (OpenGL 4.5 and DirectX 12)
Graphics Resolution				Max Digital Resolution: 7680 x 4320 at 60 Hz
Peak Single Precision FP32 Performance				2.50 TFLOPS
Mini DisplayPort Output				x4
Thermal Solution				Ultra-quiet active fansink
Slot Height				Low-Profile Single Slot
Action	Select	Select	Select	Select