NVIDIA A100 SXM4 80GB

Official
Ampere SXM 2020 7nm
FP32
19.5
TFLOPS
VRAM
80 GB
TDP
400 W
48.8 TFLOPS/kW
Bandwidth
2.0 TB/s
memory

Performance Metrics

Peak theoretical throughput by precision type

PrecisionPeak TFLOPSEfficiency
INT8 624.0 1.560 TFLOPS/W
INT4 1248.0 3.120 TFLOPS/W
FP16 312.0 0.780 TFLOPS/W
BF16 312.0 0.780 TFLOPS/W
TF32 156.0 0.390 TFLOPS/W
FP32 19.5 0.049 TFLOPS/W
FP64 9.7 0.024 TFLOPS/W
FP16 Efficiency
0.780 TFLOPS/W
312.0 TFLOPS / 400W
FP32 Efficiency
0.049 TFLOPS/W
19.5 TFLOPS / 400W

Power Specifications

TDP

400 W

Max Power

460 W

Power Connector

PCIe 16-pin

Cooling

Liquid

Memory Specifications

Capacity

80 GB

Type

--

Bandwidth

2039 GB/s

Interface

--

Hardware & Design

Form Factor

SXM

Architecture

Ampere

Process Node

7nm

Launch Year

2020

Variant

SXM4 80GB

Market Segment

Data Center

Documentation & Resources

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
$1.39 View →
DataCrunch
$1.79 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

Systems Using This GPU

Pre-configured systems featuring the NVIDIA A100

SystemPeak Performance
NVIDIA DGX A100 640GB
DGX · rack · 2020
4.99 PFLOPS
NVIDIA HGX A100 4-GPU
HGX · baseboard · 2020
2.50 PFLOPS
NVIDIA HGX A100 8-GPU
HGX · baseboard · 2020
4.99 PFLOPS

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