| | |
| Product | NVIDIA® 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 Cooler |
| Action | Select | Select |
| Main Specifications |
| Product Series |
Nvidia A2 | Nvidia A16 |
| Core Type |
NVIDIA TENSOR | NVIDIA TENSOR |
| Core Clock Speed |
1440 MHz (1770 MHz Boost Clock) | |
| Host Interface |
PCI Express 4.0 x8 | PCI Express 4.0 x16 |
| GPU Architecture |
Ampere | Ampere |
| Detailed Specifications |
| Streaming Processor Cores |
1280 CUDA Cores | |
| NVIDIA Tensor Cores |
40 | Gen 3 | |
| NVIDIA RT Cores |
10 | Gen 2 | |
| Memory Clock Speed |
6251 MHz | |
| Memory Interface |
128-bit | |
| Max Memory Size |
16 GB GDDR6 ECC | 4x 16GB GDDR6 with error-correcting code (ECC) |
| Max Memory Bandwidth |
200 GB/s | 4x 232GB/s |
| ECC Protection |
On by Default | |
| TF32 Tensor Core |
9 TFLOPS | 18 TFLOPS Sparsity | |
| FP32 |
4.5 TFLOPS | |
| Peak FP16 Tensor Core |
18 TFLOPS | 36 TFLOPS Sparsity | |
| NVIDIA CUDA™ Technology |
11.1 or later | |
| Peak INT4 Performance |
72 TOPS | 144 TOPS Sparsity | |
| Peak INT8 Performance |
36 TOPS | 72 TOPS Sparsity | |
| Cooling |
Passive | Passive |
| Dual Slot |
Single-slot | Dual-slot |
| Dimensions |
6.61” L x 2.71” H | |
| Form Factor |
Low-Profile PCIe | |
| Supplementary Power Connectors |
| 8-pin CPU |
| Max Graphics Card Power (W) |
40-60 W | Configurable | 250W |
| Action | Select | Select |