NVIDIA A30 TENSOR CORE GPU «NEW»

NEW

Bring accelerated performance to every enterprise workload with NVIDIA® A30 Tensor Core GPUs. With NVIDIA Ampere architecture Tensor Cores and Multi-Instance GPU (MIG), it delivers speedups securely across diverse workloads, including AI inference at scale and high-performance computing (HPC) applications. By combining fast memory bandwidth and low-power consumption in a PCIe form factor—optimal for mainstream servers—A30 enables an elastic data centre and delivers maximum value for enterprises.

Get a Quote

* With sparsity
** NVLink Bridge for up to two GPUs

XENON NVIDIA A30
Specifications
NVIDIA A30 Tensor Core GPU
Specifications

FP64

NVIDIA A30 Tensor Core GPU

5.2 teraFLOPS

Specifications

FP64 Tensor Core

NVIDIA A30 Tensor Core GPU

10.3 teraFLOPS

Specifications

FP32

NVIDIA A30 Tensor Core GPU

10.3 teraFLOPS

Specifications

TF32 Tensor Core

NVIDIA A30 Tensor Core GPU

82 teraFLOPS | 165 teraFLOPS*

Specifications

BFLOAT16 Tensor Core

NVIDIA A30 Tensor Core GPU

165 teraFLOPS | 330 teraFLOPS*

Specifications

FP16 Tensor Core

NVIDIA A30 Tensor Core GPU

165 teraFLOPS | 330 teraFLOPS*

Specifications

INT8 Tensor Core

NVIDIA A30 Tensor Core GPU

330 TOPS | 661 TOPS*

Specifications

INT4 Tensor Core

NVIDIA A30 Tensor Core GPU

661 TOPS | 1321 TOPS*

Specifications

Media engines

NVIDIA A30 Tensor Core GPU

  • 1 optical flow accelerator (OFA)
  • 1 JPEG decoder (NVJPEG)
  • 4 video decoders (NVDEC)
Specifications

GPU memory

NVIDIA A30 Tensor Core GPU

24GB HBM2

Specifications

GPU memory bandwidth

NVIDIA A30 Tensor Core GPU

933GB/s

Specifications

Interconnect

NVIDIA A30 Tensor Core GPU

  • PCIe Gen4: 64GB/s
  • Third-gen NVLINK: 200GB/s**
Specifications

Form factor

NVIDIA A30 Tensor Core GPU

Dual-slot, full-height, full-length (FHFL)

Specifications

Max thermal design power (TDP)

NVIDIA A30 Tensor Core GPU

165W

Specifications

Multi-Instance GPU (MIG)

NVIDIA A30 Tensor Core GPU

  • 4 GPU instances @ 6GB each
  • 2 GPU instances @ 12GB each
  • 1 GPU instance @ 24GB
Specifications

Virtual GPU (vGPU) software support

NVIDIA A30 Tensor Core GPU

  • NVIDIA AI Enterprise for VMware
  • NVIDIA Virtual Compute Server

Get a Quote Talk to a Solutions Architect