NVIDIA A100 PCIe 80GB

Ampere PCIe 2021
FP32
19.5
TFLOPS
VRAM
80 GB
HBM2e
TDP
300 W
65.0 TFLOPS/kW
Bandwidth
1.9 TB/s
memory
View Providers

Performance Metrics

Peak theoretical throughput by precision type

PrecisionPeak TFLOPSEfficiency
INT8 624.0 2.080 TFLOPS/W
INT4 1248.0 4.160 TFLOPS/W
FP16 312.0 1.040 TFLOPS/W
BF16 312.0 1.040 TFLOPS/W
TF32 156.0 0.520 TFLOPS/W
FP32 19.5 0.065 TFLOPS/W
FP64 9.7 0.032 TFLOPS/W
FP16 Efficiency
1.040 TFLOPS/W
312.0 TFLOPS / 300W
FP32 Efficiency
0.065 TFLOPS/W
19.5 TFLOPS / 300W

Power Specifications

TDP

300 W

Max Power

345 W

Power Connector

PCIe 8-pin

Cooling

Air

Memory Specifications

Capacity

80 GB

Type

HBM2e

Bandwidth

1935 GB/s

Interface

5120-bit

Hardware & Design

Form Factor

PCIe

Architecture

Ampere

Process Node

--

Launch Year

2021

Variant

PCIe 80GB

Market Segment

Data Center

Common Use Cases

LLM Training LLM Inference Scientific Computing HPC Workloads

The NVIDIA A100 is optimized for high-performance computing tasks with Ampere architecture delivering 19.5 TFLOPS of compute power.

Where to Rent

ProviderPrice/hr
RunPod
$1.19 View →

Prices shown are approximate. Click through for current pricing.

Similar GPUs

NVIDIA RTX A6000 48GB

PCIe · 2020
FP32: 38.7 TFLOPS
Compare vs RTX A6000

NVIDIA A40 48GB

PCIe · 2021
FP32: 37.4 TFLOPS
Compare vs A40

NVIDIA A10G 24GB

PCIe · 2022
FP32: 35.0 TFLOPS
Compare vs A10G

Stay Updated on GPU Releases

Get notified when new GPUs are added or specifications are updated.

Loading verification...

No spam, unsubscribe anytime.

Back to GPUs