NVIDIA A100

PNY-Technologies-
NVIDIA A100

NVIDIA® A100 – NVA100TCGPU-KIT

The Most Powerful Compute Platform for Every Workload
The NVIDIA A100 Tensor Core GPU delivers unprecedented acceleration—at every scale—to power the world’s highest performing elastic data centers for AI, data analytics, and high-performance computing (HPC) applications. As the engine of the NVIDIA data center platform, A100 provides up to 20x higher performance over the prior NVIDIA Volta generation.

Part NumberNVA100TCGPU-KIT
CUDA Cores6912
Streaming Multiprocessors108
Tensor Cores | Gen 3432
GPU Memory48 GB HBM2e ECC on by Default
Memory Interface5120-bit
Memory Bandwidth1555 GB/s
NVLink2-Way, 2-Slot, 600 GB/s Bidirectional
MIG (Multi-Instance GPU) SupportYes, up to 7 GPU Instances
FP649.7 TFLOPS
FP64 Tensor Core19.5 TFLOPS
FP3219.5 TFLOPS
TF32 Tensor Core156 TFLOPS | 312 TFLOPS**
BFLOAT16 Tensor Core312 TFLOPS | 624 TFLOPS**
FP16 Tensor Core312 TFLOPS | 624 TFLOPS**
INT8 Tensor Core624 TOPS | 1248 TOPS**
INT4 Tensor Core1248 TOPS | 2496 TOPS**
Thermal SolutionPassive
vGPU SupportNVIDIA Virtual Compute Server (vCS)
System InterfacePCIE 4.0 x16
Maximum Power Consumption250 W

PNY carries NVIDIA A100 inventory in stock for immediate delivery, offers extensive pre- and post-sales support, and unrivaled customer service.