NVIDIA A2, 16GB 6251MHz, GDDR6 128-bit, 200GB/s, PCIe Gen4 x8, Single Slot, 40-60W, Tensor Core GPU, ATX, Ampere, 2YR Warranty

The NVIDIA A2 Tensor Core GPU is Powered by the NVIDIA Ampere architecture represents a significant advancement in GPU technology. It has a Single Slot card featuring 16 GB of GDDR6 memory and a 60W maximum power limit. The A2 supports x8 PCIe Gen4 connectivity. It is a Passively cooled card with a superior thermal design that requires system airflow to operate and handles challenging ambient environments with ease (NEBS-3 capable). A2's versatility, compact size, and low power exceed the demands for edge deployments at scale, instantly upgrading existing entry-level CPU servers to handle inference

Peak FP32: 4.5 TFTF32 Tensor Core: 9 TFBFLOAT16 Tensor Core: 18 TFPeak FP16 Tensor Core: 18 TFPeak INT8 Tensor Core: 36 TOPSPeak INT4 Tensor Core: 72 TOPSRT Cores: 10Media engines: 1 video encoder, 2 video decoders (includes AV1 decode)GPU memory: 16GB GDDR6GPU memory bandwidth: 200GB/sInterconnect: PCIe Gen4 x8Form factor: 1-slot, low-profile PCIeMax thermal design power (TDP): 40 - 60W (configurable)Virtual GPU (vGPU) software support: NVIDIA Virtual PC (vPC), NVIDIA Virtual Applications (vApps), NVIDIA RTX Virtual Workstation (vWS), NVIDIA AI Enterprise, NVIDIA Virtual Compute Server (vCS)
Peak FP32: 4.5 TF
TF32 Tensor Core: 9 TF
BFLOAT16 Tensor Core: 18 TF
Peak FP16 Tensor Core: 18 TF
Peak INT8 Tensor Core: 36 TOPS
Peak INT4 Tensor Core: 72 TOPS
RT Cores: 10
Media engines: 1 video encoder, 2 video decoders (includes AV1 decode)
GPU memory: 16GB GDDR6
GPU memory bandwidth: 200GB/s
Interconnect: PCIe Gen4 x8
Form factor: 1-slot, low-profile PCIe
Max thermal design power (TDP): 40 - 60W (configurable)
Virtual GPU (vGPU) software support: NVIDIA Virtual PC (vPC), NVIDIA Virtual Applications (vApps), NVIDIA RTX Virtual Workstation (vWS), NVIDIA AI Enterprise, NVIDIA Virtual Compute Server (vCS)