Architecture | Ampere |
GPU memory | 16GB GDDR6 |
Memory Bandwidth | 200GB/s |
Peak FP32 | 4.5 TF |
TF32 Tensor Core | 9 TF || 18 TF with sparsity |
BFLOAT16 Tensor Core | 18 TF || 36 TF with sparsity |
Peak FP16 Tensor Core | 18 TF || 36 TF with sparsity |
Peak INT8 Tensor Core | 36 TOPS || 72 TOPS with sparsity |
Peak INT4 Tensor Core | 72 TOPS || 144 TOPS with sparsity |
RT Cores | 10 |
Media Engines | 1 * video decoder |
2 * video decoders | |
Includes AV1 decode | |
Interconnect | PCIe Gen4 x8 |
Form Factor | 1-slot, LP PCIe |
Max Thermal Design Power (TDP) | 40-60W (Configurable) |
vGPU Support | NVIDIA Virtual PC (vPC) |
NVIDIA Virtual Applications (vApps) | |
NVIDIA RTX Virtual Workstations (vWS) | |
NVIDIA AI Enterprise | |
NVIDIA Virtual Compute Server (vCS) |