ProductNVIDIA® A2 GPU Computing Accelerator - 16GB GDDR6 - PCIe 4.0 x8 - Passive Cooler (w/o CEC)NVIDIA® A16 GPU Computing Accelerator - 64GB (4x 16GB) GDDR6 - PCIe 4.0 x16 - Passive CoolerNVIDIA® A30 GPU Computing Accelerator - 24GB HBM2 - PCIe 4.0 x16 - Passive CoolerNVIDIA® A40 GPU Computing Accelerator - 48GB GDDR6 - PCIe 4.0 x16 - Passive Cooling (w/o CEC)NVIDIA® RTX A6000 - 48GB GDDR6 - PCIe 4.0 x16 - Active Cooling (4xDP)
ActionSelectSelectSelectSelectSelect
Main Specifications
Product Series Nvidia A2Nvidia A16Nvidia A30Nvidia A40
Core Type NVIDIA TENSORNVIDIA TENSORNVIDIA TENSORNVIDIA TENSOR
Core Clock Speed 1440 MHz (1770 MHz Boost Clock)
Host Interface PCI Express 4.0 x8PCI Express 4.0 x16PCI Express 4.0 x16PCI Express 4.0 x16PCI Express 4.0 x16
GPU Architecture AmpereAmpereAmpereAmpere
Product Type Workstation
Product Line NVIDIA Professional Graphics
Memory Technology GDDR6
Memory Capacity 48 GB
Detailed Specifications
Streaming Processor Cores 1280 CUDA Cores10752 CUDA Cores10752 Shading Units
NVIDIA Tensor Cores 40 | Gen 3336 Tensor Cores336
NVIDIA RT Cores 10 | Gen 284 RT Cores84
Memory Clock Speed 6251 MHz2000 MHz 16 Gbps effective
Memory Interface 128-bit384-bit384-bit
Memory Speeds (GT/s) 14.5Gbps GDDR6
Max Memory Size 16 GB GDDR6 ECC4x 16GB GDDR6 with error-correcting code (ECC)24 GB HBM248 GB GDDR6 with error-correcting code (ECC)
Max Memory Bandwidth 200 GB/s4x 232GB/s933 GB/s696 GB/s
Peak FP64 5.2 teraFLOPS
Peak FP64 Tensor Core 10.3 teraFLOPS
INT8 Tensor Core 330 TOPS | 661 TOPS
TF32 Tensor Core 9 TFLOPS | 18 TFLOPS Sparsity82 teraFLOPS | 165 teraFLOPS
FP32 4.5 TFLOPS10.3 teraFLOPS
Peak BFLOAT16 Tensor Core 165 teraFLOPS | 330 teraFLOPS
Peak FP16 Tensor Core 18 TFLOPS | 36 TFLOPS Sparsity165 teraFLOPS | 330 teraFLOPS
Peak INT4 Tensor Core 661 TOPS | 1321 TOPS
Total NVLink Bandwidth Third-gen NVLINK: 200GB/sNVIDIA NVLink 112.5 GB/s (bidirectional) PCIe Gen4 16 GB/s
NVIDIA CUDA™ Technology 11.1 or laterYes
Peak INT4 Performance 72 TOPS | 144 TOPS Sparsity
Peak INT8 Performance 36 TOPS | 72 TOPS Sparsity
ECC Protection On by Default
Transistor Count 28.3 Billion
DisplayPort Connectors 3x DisplayPort 1.4
A40 is configured for virtualization by default with physical display connectors disabled. The display outputs can be enabled via management software tools.
Cooling PassivePassivePassive
Dual Slot Single-slotDual-slotDual-slot2-slot Low-profile
Dimensions 6.61” L x 2.71” H4.4" (H) x 10.5" (L)4.4" (H) x 10.5" (L)
Form Factor Low-Profile PCIe
Lithography Samsung 8nmSamsung 8nm
Supplementary Power Connectors 8-pin CPU1x 8-pin CPU (EPS12V)1x 8-pin CPU (EPS12V)1x 8-pin EPS
Max Graphics Card Power (W) 40-60 W | Configurable250W165W300W300W
Processor Ampere (GA102)
Memory Bandwidth 768 GB/s
Core Clock Speed 1455 MHz Base Clock
1860 MHz Boost Clock
L2 Cache Size 6 MB
API Support CUDA 8.5, OpenCL 2.0
Shader Model 6.5, OpenGL 4.6, DirectX 12 Ultimate (12_2), Vulkan 1.2
Texture Fill Rate 625 GTexel/s
Graphics Resolution 7680 x 4320 x36 bpp at 60 Hz
Peak Double Precision FP64 Performance 1,250 GFLOPS (1:32)
Peak Single Precision FP32 Performance 38.7 TFLOPS
Peak Half Precision FP16 Performance 40.00 TFLOPS (1:1)
Multi-GPU Scalability NVLINK 2-way low profile (2-slot and 3-slot bridges) connects 2x NVIDIA RTX A6000
NVLink Interconnect 112.5 GB/s (bidirectional)
VR Ready Yes
Vulkan API 1.2
DisplayPort Output 4x DisplayPort 1.4a
Minimum Recommended Power, Single Card (W) 700W
Minimum Recommended Power, 2-Way (W) 850
Minimum Recommended Power, 3-Way (W) 1000
Minimum Recommended Power, 4-Way (W) 1200
Thermal Solution Active Heatsink
Slot Height 2-Slot
ActionSelectSelectSelectSelectSelect