PNY NVIDIA A30 Modul 24GB HBM2 (TCSA30M-PB)

NVIDIA A30 GPU with Tensor Cores — the most versatile GPU for mainstream computing, designed for AI inference and core enterprise workloads. Based on the NVIDIA Ampere architecture with Tensor Core technology, it supports a wide range of math calculations, providing a single accelerator to accelerate every workload. The same compute resource built for AI inference at scale can quickly retrain AI models with TF32, and accelerate high-performance computing (HPC) applications with FP64 Tensor Cores. Multi-Instance GPU (MIG) and FP64 Tensor Cores combine with fast memory bandwidth of 933 gigabytes per second (GB/s) at low power consumption of 165W, all running on a PCIe card optimal for mainstream servers .