NVIDIA Tesla A30 24G HBM2 Graphics Card for Design, Deep Learning, AI, and Professional Data Computing Bargaining

FP64 Peak Performance：5.2 TF

FP64 Tensor Core Peak Performance： 10.3 TF

FP32 Peak Performance：10.3 TF

TF32 Tensor Core：82 TF | 165 TF*

BFLOAT16 Tensor Core：165 TF | 330 TF*

FP16 Tensor Core Peak Performance： 165 TF | 330 TF*

INT8 Tensor Core Peak Performance：330 TOPS | 661 TOPS*

INT4 Tensor Core Peak Performance：661 TOPS | 1321 TOPS*

Media Engine：1 Optical Flow Accelerator (OFA)1 JPEG Decoder (NVJPEG)4 Video Decoders (NVDEC)

GPU Memory：24GB HBM2

GPU Memory Bandwidth：933 GB/s

Interconnect：PCIe 4th Generation: 64GB/sNVIDIA® NVLINK® 3rd Generation 200GB/s**

Form Factor：Dual-slot, Full Height, Full Length (FHFL)

Maximum Thermal Design Power (TDP)：165 Watts

Multi-Instance GPU (MIG)：4 MIGs, 6GB each2 MIGs, 12GB each1 MIG, 24GB

Virtual GPU (vGPU) Software Support：NVIDIA AI Enterprise Software Suite for VMwareNVIDIA Virtual Compute Server.