16 GB, GDDR6, 128-bit, PCI Express 4.0 x8, 2560 CUDA Cores

Description

Versatile Entry-Level Inference The NVIDIA A2 Tensor Core GPU provides entry-level inference with low power, a small footprint, and high performance for NVIDIA AI at the edge. Featuring a low-profile PCIe Gen4 card and a low 40-60 watt (W) configurable thermal design power (TDP) capability, the A2 brings adaptable inference acceleration to any server. A2's versatility, compact size, and low power exceed the demands for edge deployments at scale, instantly upgrading existing entrylevel CPU servers to handle inference. Servers accelerated with A2 GPUs deliver higher inference performance versus CPUs and more efficient intelligent video analytics (IVA) deployments than previous GPU generations—all at an entry-level price point.

Specifications

Processor
Graphics processor family	NVIDIA
CUDA cores	2560
CUDA	Yes
Graphics processor	A2
Memory
Discrete graphics card memory	16 GB
Memory bandwidth (max)	200 GB/s
Memory bus	128 bit
Graphics card memory type	GDDR6
Ports & interfaces
Interface type	PCI Express x8 4.0
Video
DirectX version	No
Shader model version	No
OpenGL version	No
Dual Link DVI	No
CUDA cores	2560
Performance
DirectX version	No
Shader model version	No
OpenGL version	No
Dual Link DVI	No
TV tuner integrated	No
Design
Cooling type	Passive
Product colour	Beige
Number of slots	1
Bracket height	Low-Profile (LP)
Power
Power consumption (max)	60 W
Weight & dimensions
Number of slots	1
Weight	260 g
Technical details
Cooling type	Passive
Product colour	Beige
TV tuner integrated	No
Harmonized System (HS) code	84733020
Logistics data
Harmonized System (HS) code	84733020