NVIDIA RTX A2000 12GB

Ampere PCIe 2022 8nm

Overview

8.0

FP32 TFLOPS

12 GB

Memory GDDR6

288 GB/s

Memory Bandwidth

70 W

TDP

Performance Metrics

Precision	Peak (dense)	2:4 Sparse	Bits	Type
FP64	0.1	N/A	64	Standard
FP32	8.0	N/A	32	Standard
TF32	8.0	not published	32	Standard
BF16	8.0	not published	16	Standard
FP16	8.0	not published	16	Standard
FP8	—	not published	—	Standard
FP6	—	not published	—	Standard
FP4	—	not published	—	Standard
INT8	16.0	not published	8	Standard

Memory Specifications

Capacity: 12 GB
Type: GDDR6
Bandwidth: 288 GB/s
Interface Width: 192-bit

Power & Efficiency

TDP: 70 W
Max power (Flopper estimate): ~81 W est.
FP32 dense TFLOPS per W of TDP: 0.11 TFLOPS/W
FP16 dense TFLOPS per W of TDP: 0.11 TFLOPS/W

Flopper estimate: 70 W TDP x 1.15. The vendor publishes no maximum board power for this part. Per W of TDP figures divide dense peak by accelerator TDP. Board power only: excludes host CPUs, networking, cooling and facility overhead.

Hardware Details

Vendor: NVIDIA

Architecture: Ampere

Process Node: 8nm

Form Factor: PCIe

Launch Year: 2022

Variant: 12GB

Compute Engine

CUDA Cores: 3,328

Tensor Cores: 104 (3rd Gen)

SMs: 26

Base Clock: 562 MHz

Boost Clock: 1.20 GHz

Enterprise Features

Sparsity: Yes