Interactive 3D Model

Loading viewer...

Drag to rotate ┬╖ Scroll to zoom

ARCHITECTURE

Ampere

SERIES

A100

Memory

80GB HBM2e

Bandwidth

2.0 TB/s

TDP

400W

In StockA100┬╖Best for: Enterprise AI

NVIDIA A100 Tensor Core GPU

Ampere

|Data Center GPUs

Overview

The NVIDIA A100 Tensor Core GPU is the proven workhorse for enterprise AI, HPC, and data analytics. With 80GB HBM2e memory and Multi-Instance GPU (MIG) technology, the A100 delivers reliable performance across diverse workloads.

Key Features

80GB HBM2e
MIG
NVLink 3.0

Ideal Use Cases

ai trainingdata analytics

Full Specifications

Complete technical specifications for the A100.

Memory

Memory: 80GB HBM2e
Memory Bandwidth: 2.0 TB/s

Compute

Tensor Cores: 432
CUDA Cores: 6912
FP8 TFLOPS: —
FP16 TFLOPS: 312
TF32 TFLOPS: 156
FP64 TFLOPS: 19.5

Interconnect

Interconnect: NVLink 3.0, 600GB/s

Physical

TDP: 400W
Form Factor: SXM4
Cooling: Liquid Cooled

Manufacturing

Launch Date: Q3 2021
Manufacturing Process: 7nm

Ready to deploy the A100?

Get a personalized quote within 24 hours. Our NVIDIA-certified engineers will help you architect the optimal configuration for your workload.

Related Chips

More chips in Data Center GPUs.

H100

In Stock

NVIDIA H100 Tensor Core GPU

Enterprise AI training and inference GPU with Transformer Engine and FP8 precision.

ArchitectureHopper

Memory80GB HBM3

TDP700W

H200

In Stock

NVIDIA H200 Tensor Core GPU

Next-gen AI GPU with 141GB HBM3e memory for larger models and faster inference.

ArchitectureHopper

Memory141GB HBM3e

TDP700W

B200

Pre-Order

NVIDIA B200 Tensor Core GPU

Flagship AI GPU with Blackwell architecture, 384GB HBM3e, and 10 TB/s bandwidth.

ArchitectureBlackwell

Memory384GB HBM3e

TDP1000W

GH200

On Order

NVIDIA GH200 Grace Hopper

Superchip combining Grace CPU with Hopper GPU for HPC and AI workloads.

ArchitectureHopper

Memory96GB HBM3 + 480GB LPDDR5X

TDP—