PRODUCT DESCRIPTION
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 HPC. Powered by the NVIDIA Ampere Architecture, A100 is the engine of the NVIDIA data center platform. A100 provides up to 20X higher performance over the prior generation and can be partitioned into seven GPU instances to dynamically adjust to shifting demands. The A100 80GB debuts the world’s fastest memory bandwidth at over 2 terabytes per second (TB/s) to run the largest models and datasets.

PRODUCT SPECIFICATIONS
Model: A100 80GB PCIe
FP64: 9.7 TFLOPS
FP64 Tensor Core: 19.5 TFLOPS
FP32: 19.5 TFLOPS
Tensor Float 32 (TF32): 156 TFLOPS | 312 TFLOPS*
BFLOAT16 Tensor Core: 312 TFLOPS | 624 TFLOPS*
FP16 Tensor Core: 312 TFLOPS | 624 TFLOPS*
INT8 Tensor Core: 624 TOPS | 1248 TOPS*
GPU Memory: 80GB HBM2e
GPU Memory Bandwidth: 1,935 GB/s
Max Thermal Design Power (TDP): 300W
Multi-Instance GPU: Up to 7 MIGs @ 10GB
Form Factor: PCIe Dual-slot air-cooled or single-slot liquid-cooled
Interconnect: NVIDIA® NVLink® Bridge for 2 GPUs: 600 GB/s ** PCIe Gen4: 64 GB/s
Server Options: Partner and NVIDIA-Certified Systems™ with 1-8 GPUs