DATASHEET

NVIDIA RTX A2000 | A2000 12GB

Compact Design. Unmatched Performance.

Accelerate Your Workflow SPECIFICATIONS

GPU memory
The NVIDIA RTX ™ A2000 brings the power of NVIDIA RTX technology, real-
NVIDIA RTX A2000 6GB GDDR6
time ray tracing, AI-accelerated compute, and high-performance graphics to NVIDIA RTX A2000 12GB 12GB GDDR6
more professionals. Built on the NVIDIA Ampere architecture, the VR ready
Memory interface 192-bit
RTX A2000 combines 26 second-generation RT Cores, 104 third-generation
Memory bandwidth 288 GB/s
Tensor Cores, and 3,328 next-generation CUDA® cores and 6 or 12GB of
Error-correcting code (ECC) Yes
GDDR6 graphics memory with error correction code (ECC) support for error
free computing. RTX A2000 GPUs feature a power-efficient low profile, NVIDIA Ampere architecture-
3,328
based CUDA Cores
dual-slot PCIe form factor that fits into a wide range of small form factor
NVIDIA third-generation
workstations, and the RTX A2000 12GB doubles memory for even larger Tensor Cores
104
models and datasets. Design bigger, render faster, and work smarter than
NVIDIA second-generation
ever before with RTX A2000 GPUs. 26
RT Cores
NVIDIA RTX professional graphics cards are certified with a broad range of Single-precision performance 8.0 TFLOPS2
professional applications, tested by leading independent software vendors RT Core performance 15.6 TFLOPS2
(ISVs) and workstation manufacturers, and backed by a global team of Tensor performance 63.9 TFLOPS3
support specialists. Get the peace of mind needed to focus on what matters System interface PCIe 4.0 x16
with the premier visual computing solution for mission-critical business.
Power consumption Total board power: 70 W
Thermal solution Active
Features Form factor 2.7” H x 6.6” L, dual slot
Display connectors 4x mDP 1.4a
> PCI Express Gen 4 > NVIDIA RTX Experience™
with latching mechanism
> Four Mini DisplayPort 1.4a > NVIDIA RTX Desktop Manager Max simultaneous displays 4x 4096 x 2160 @ 120 Hz,
connectors with latching software 4x 5120 x 2880 @ 60 Hz
mechanism
> HDCP 2.2 support 2x 7680 x 4320 @ 60 Hz
> AV1 decode support Encode/decode engines 1x encode, 1x decode
> NVIDIA Mosaic1 technology
(+AV1 decode)
> DisplayPort with audio
VR ready Yes
Graphics APIs DirectX 12 Ultimate,
Shader Model 6.6,
OpenGL 4.64, Vulkan 1.34
1 Windows 10, Windows 11, and Linux. | 2 Peak rates based on GPU Boost Clock. | 3 Effective teraFLOPS (TFLOPS) using Compute APIs CUDA 11.6, DirectCompute,
the new sparsity feature. | 4 Product is based on a published Khronos specification and is expected to pass the Khronos OpenCL 3.0
conformance testing process when available. Current conformance status can be found at www.khronos.org/conformance

Learn more To learn more about the NVIDIA RTX A2000 or NVIDIA RTX A2000 12GB, visit www.nvidia.com/rtx-a2000/

© 2022 NVIDIA Corporation and Affiliates. All rights reserved. NVIDIA, the NVIDIA logo, CUDA, RTX Experience, and RTX are trademarks and/or registered trademarks of NVIDIA Corporation and Affiliates in the U.S. and
NVIDIA
other countries. Other company and product names may be trademarks of the respective companies with which they are associated. All other trademarks are property of their RTX A2000
respective | MAY22
owners. DATASHEET | AUG21