NVIDIA RTX A4500 20GB

Ampere PCIe 2021 8nm

Overview

23.6

FP32 TFLOPS

20 GB

Memory GDDR6

640 GB/s

Memory Bandwidth

200 W

TDP

Performance Metrics

Precision	Peak (dense)	2:4 Sparse	Bits	Type
FP64	0.4	N/A	64	Standard
FP32	23.6	N/A	32	Standard
TF32	23.6	not published	32	Standard
BF16	23.6	not published	16	Standard
FP16	23.6	not published	16	Standard
FP8	—	not published	—	Standard
FP6	—	not published	—	Standard
FP4	—	not published	—	Standard
INT8	47.3	not published	8	Standard

Memory Specifications

Capacity: 20 GB
Type: GDDR6
Bandwidth: 640 GB/s
Interface Width: 320-bit

Power & Efficiency

TDP: 200 W
Max power (Flopper estimate): ~230 W est.
FP32 dense TFLOPS per W of TDP: 0.12 TFLOPS/W
FP16 dense TFLOPS per W of TDP: 0.12 TFLOPS/W

Flopper estimate: 200 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: 2021

Variant: 20GB

Compute Engine

CUDA Cores: 7,168

Tensor Cores: 224 (3rd Gen)

SMs: 56

Base Clock: 1.05 GHz

Boost Clock: 1.65 GHz

Enterprise Features

Sparsity: Yes