NVIDIA RTX A6000 48GB

Ampere PCIe 2020 8nm

Overview

38.7

FP32 TFLOPS

48 GB

Memory

768 GB/s

Memory Bandwidth

300 W

TDP

Performance Metrics

Precision	Peak (dense)	2:4 Sparse	Bits	Type
FP64	0.6	N/A	64	Standard
FP32	38.7	N/A	32	Standard
TF32	77.4	154.8	32	Standard
BF16	154.8	309.6	16	Standard
FP16	154.8	309.6	16	Standard
FP8	—	not published	—	Standard
FP6	—	not published	—	Standard
FP4	—	not published	—	Standard
INT8	309.7	619.4	8	Standard
INT4	619.3	1238.6	4	Standard

Memory Specifications

Capacity: 48 GB
Type: —
Bandwidth: 768 GB/s
Interface Width: —

Power & Efficiency

TDP: 300 W
Max power (Flopper estimate): ~345 W est.
FP32 dense TFLOPS per W of TDP: 0.13 TFLOPS/W
FP16 dense TFLOPS per W of TDP: 0.52 TFLOPS/W

Flopper estimate: 300 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: 2020

Variant: 48GB

Enterprise Features

Sparsity: Yes