Introduction

NVIDIA A30 Tensor Core GPU is the most versatile mainstream compute GPU for AI inference and mainstream enterprise workloads. Powered by NVIDIA Ampere architecture Tensor Core technology, it supports a broad range of math precisions, providing a single accelerator to speed up every workload. Built for AI inference at scale, the same compute resource can rapidly re-train AI models with TF32, as well as accelerate high-performance computing (HPC) applications using FP64 Tensor Cores. Multi-Instance GPU (MIG) and FP64 Tensor Cores combine with fast 933 gigabytes per second (GB/s) of memory bandwidth in a low 165W power envelope, all running on a PCIe card optimal for mainstream servers.

Processor

CUDA

Y

CUDA cores

3804

Graphics processor family

NVIDIA

Graphics processor

A30

Parallel processing technology support

Not supported

FireStream

N

Memory

Discrete graphics card memory

24 GB

Graphics card memory type

High Bandwidth Memory 2 (HBM2)

Memory bus

3072 bit

Memory bandwidth (max)

933 GB/s

Ports & interfaces

Interface type

PCI Express x16 4.0

Performance

TV tuner integrated

N

Dual Link DVI

N

Design

Cooling type

Passive

Form factor

Full-Height/Full-Length (FH/FL)

Bracket height

Full-Height (FH)

Number of slots

2

Product colour

Beige

Power

Power consumption (typical)

165 W

Supplementary power connectors

1x 8-pin

Weight & dimensions

Weight

1.02 kg

Depth

267.7 mm

Height

111.2 mm