Nvidia RTX A4000 Datasheet
Nvidia RTX A4000 Datasheet
Nvidia RTX A4000 Datasheet
192 third-generation Tensor Cores, and 6,144 CUDA® cores with 16GB of NVIDIA Ampere architecture- 6,144
based
graphics memory with error-correction code (ECC) so you can innovate with CUDA Cores
uncompromised computing accuracy and reliability. The RTX A4000 also NVIDIA third-generation 192
features a power-efficient, single-slot PCIe form factor that fits into a wide Tensor Cores
range of workstation chassis, so you can do exceptional work without limits. NVIDIA second-generation 48
RT Cores
NVIDIA RTX professional graphics cards are certified with a broad range of Single-precision performance 19.2 TFLOPS3
professional applications, tested by leading independent software vendors RT Core performance 37.4 TFLOPS3
(ISVs) and workstation manufacturers, and backed by a global team of support Tensor performance 153.4 TFLOPS4
specialists. Get the peace of mind needed to focus on what matters with the System interface PCIe 4.0 x16
premier visual computing solution for mission-critical business. Power consumption Total board power: 140 W
Thermal solution Active
Features Form factor 4.4” H x 9.5” L,
single slot
> PCI Express Gen 4 > NVIDIA Quadro® Sync II1
compatibility Display connectors 4x DisplayPort 1.4a
> Four DisplayPort 1.4a connectors
Max simultaneous displays 4x 4096 x 2160 @ 120 Hz,
> NVIDIA RTX Experience™
> AV1 decode support 4x 5120 x 2880 @ 60 Hz,
2x 7680 x 4320 @ 60 Hz
> NVIDIA RTX Desktop Manager
> DisplayPort with audio
software Power connector 1x 6-pin PCIe
> 3D stereo support with stereo Encode/decode engines 1x encode, 1x decode
> NVIDIA RTX IO support
connector (+AV1 decode)
> HDCP 2.2 support VR ready Yes
> NVIDIA GPUDirect® for
Video support > NVIDIA Mosaic technology
2
Graphics APIs DirectX 12 Ultimate ,
Shader Model 6.6,
1 Quadro Sync II card sold separately. | 2 Windows 10, Windows 11, and Linux. | 3 Peak rates based on GPU Boost OpenGL 4.65, Vulkan 1.35
Clock. | 4 Effective teraFLOPS (TFLOPS) using the new sparsity feature. | 5 Product is based on a published Khronos
specification and is expected to pass the Khronos conformance testing process when available. Current conformance Compute APIs CUDA 11.6, DirectCompute,
status can be found at www.khronos.org/conformance OpenCL 3.0
Learn more
© 2022 NVIDIA Corporation. All rights reserved. NVIDIA, the NVIDIA logo, CUDA, GPUDirect, NVLink, Quadro, RTX Experience, and RTX are
trademarks and/or registered trademarks of NVIDIA Corporation in the U.S. and 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 respective owners. MAY22 NVIDIA RTX A2000
A4000 | DATASHEET | AUG21
May22