NVIDIA A16 Enterprise 64GB 250W
Datacenter
NVIDIA A16 Enterprise 64GB 250W

NVIDIA A16 is a PCI Express Gen4 graphics processing unit (GPU) card that is ideal for providing high-user density for Virtual Desktop Infrastructure (VDI) environments. It is a full height, full length (FHFL) design with four GPUs on a single board. The A16 is a dual-slot card featuring 64 GB of GDDR6 memory and a 250 W maximum power limit. The A16 also supports x16 PCIe Gen4 connectivity. It is a passively cooled card with a superior thermal design that requires system airflow to operate and handles challenging ambient environments with ease (NEBS-3 capable).

$3,707
The World’s Most Powerful Ray Tracing GPU
The World’s Most Powerful Ray Tracing GPU
Accelerating Innovation

Need enhanced AI, HPC, or graphics performance? NVIDIA® Accelerators for HPE offer solutions for critical scientific, industrial, and business challenges. They enable complex content visualization, big data insights, and future city reimaginations. HPE servers with NVIDIA accelerators deliver unparalleled acceleration for the era of elastic computing.

Specifications
Specifications
Feature

GPU Architecture: NVIDIA Ampere
Tensor Cores: 160 total (40 per GPU, 4 GPUs)
CUDA Cores: 5120 total FP32 (1280 per GPU, 4 GPUs)
RT Cores: 40 total (10 per GPU, 4 GPUs)
Double-Precision Performance: Not applicable
Single-Precision Performance: FP32: 4x 4.5 TFLOPS, TF32: 4x 9 TFLOPS, 4x 18 TFLOPS*
Half-Precision Performance: FP16: 4x 17.9 TFLOPS, 4x 35.9 TFLOPS*
Bfloat16: Not applicable
Integer Performance: INT8: 4x 35.9 TOPS, 4x 71.8 TOPS*
GPU Memory: 64GB GDDR6 (16 GB per GPU, 4 GPUs)

Specifications
Specifications
Feature

Memory Bandwidth: 4x 200 GB/s
ECC Support: Yes
Interconnect Bandwidth: Not applicable
System Interface: PCIe Gen 4, x16 lanes
Form Factor: PCIe full height/length, double width (dual slot)
Multi-Instance GPU (MIG): No support
Max Power Consumption: 250 W
Thermal Solution: Passive
Graphics APIs: DirectX 12.07, Shader Model 5.17, OpenGL 4.68, Vulkan 1.18 Compute APIs: CUDA, DirectCompute, OpenCL, OpenACC

Gallery
Test1
Test 2
Test 3
Test 4
Origin
Elgota
Amazon
Best Buy
New Egg
Asus
Noon
Stripe
Amazon Pay
Paypal