PNY NVIDIA A2 Datacenter Graphics Card 16GB GDDR6

PNY NVIDIA A2 Datacenter Graphics Card 16GB GDDR6

$1,399.00
{{option.name}}: {{selected_options[option.position]}}
{{value_obj.value}}

Contact us at frontdesk@c3aero.com for Purchase Orders MFN: NVA2TCGPUNC-KIT Affordable AI GPU that brings NVIDIA AI to any server or datacenter. See the full specifications and datasheet here The A2 Tensor Core GPU from PNY and NVIDIA provides entry-level inference withlow power, a small footprint, and high performance for NVIDIA AI atthe edge. Featuring a low-profile PCIe Gen4 card and a low 40-60watt (W) configurable thermal design power (TDP) capability, the A2brings adaptable inference acceleration to any server. A2's versatility, compact size, and low power exceed the demandsfor edge deployments at scale, instantly upgrading existing entrylevelCPU servers to handle inference. Servers accelerated with A2GPUs deliver higher inference performance versus CPUs and moreefficient intelligent video analytics (IVA) deployments than previousGPU generations—all at an entry-level price point. NVIDIA-Certified Systems™ featuring A2 GPUs and NVIDIA AI,including the NVIDIA Triton™ Inference Server, deliver breakthroughinference performance across edge, data center, and cloud.They ensure that AI-enabled applications deploy with fewer serversand less power, resulting in easier deployments, faster insights, andsignificantly lower costs. Technical Specifications Specification Details PNY Part Number NVA2TCGPU-KIT Peak FP32 4.5 TF TF32 Tensor Core 9 TF | 18 TF1 BFLOAT16 Tensor Core 18 TF | 36 TF1 Peak FP16 Tensor Core 18 TF | 36 TF1 Peak INT8 Tensor Core 36 TOPS | 72 TOPS1 Peak INT4 Tensor Core 72 TOPS | 144 TOPS1 RT Cores 10 Media engines 1 video encoder2 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) vGPU software support2 NVIDIA Virtual PC (vPC),NVIDIA Virtual Applications (vApps),NVIDIA RTX Virtual Workstation (vWS),NVIDIA AI Enterprise,NVIDIA Virtual Compute Server (vCS) 1 With sparsity 2 Supported in future vGPU release  

Show More Show Less