Accelerate Your Workflow
The NVIDIA RTX™ A2000 brings the power of NVIDIA RTX technology, real time ray tracing, AI-accelerated compute, and high-performance graphics to more professionals. Built on the NVIDIA Ampere architecture, the VR ready RTX A2000 combines 26 second-generation RT Cores, 104 third generation Tensor Cores, and 3,328 next-generation CUDA® cores and 6GB of GDDR6 graphics memory with error correction code (ECC) support for error free computing. The RTX A2000 features a power-efficient low profile, dual-slot PCIe form factor that fits into a wide range of small form factor workstations. Design bigger, render faster, and work smarter than ever before with the RTX A2000.
NVIDIA RTX professional graphics cards are certified with a broad range of professional applications, tested by leading independent software vendors (ISVs) and workstation manufacturers, and backed by a global team of support specialists. Get the peace of mind needed to focus on what matters with the premier visual computing solution for mission-critical business.

Features
• PCI Express Gen 4.
• Four Mini DisplayPort 1.4a connectors with latching mechanism.
• AV1 decode support.
• DisplayPort with audio.
• NVIDIA RTX Experience™.
• NVIDIA RTX Desktop Manager software.
• HDCP 2.2 support.
• NVIDIA Mosaic technology.

Key Specifications
Graphics Chipset     NVIDIA RTX A2000
Edition     RTX A2000
Manufacturing process     8 nm
Microarchitecture     Ampere
GPU Name      
Cores & Clocks
NVIDIA CUDA Cores     3328
Core Clock      
Boost Clock      
Video Memory (VRAM)
Memory Size     6 GB
Memory Type     GDDR6
Memory Clock      
Memory Bit Rate     192 Bit
Memory Bandwidth     288 GB/s
ECC Technology     Yes
Cooling
Cooling     Single Fan (1)
I/O & Connectivity
Interface     PCIe 4.0 (x16) [PCIe 3.0 Backwards Compatible]
Interface Bandwidth      
Graphics Output     4 x Mini DisplayPort 1.4
Visuals
Multi GPU Support      
NVLink Support     N/A
Total NVLink Bandwidth     N/A
Microsoft DirectX Support     12 API
HDCP Ready     Yes
Multi Monitor Support     4 Displays
Concurent Users     N/A
H.264 1080p30 Streams     N/A
Maximum Digital Resolution      
Maximum VGA Resolution      
Supported Graphics APIs    
    DirectX 12.0
    OpenGL 4.6
    Shader Model 5.1
    Vulkan 1.2

Compute Performance
Supported Compute APIs    
    CUDA
    DirectCompute
    OpenCL

Single Precision (FP32) Processing     Yes
Single Precision (FP32) Performance      
Double Precision (FP64) Processing     No
Double Precision (FP64) Performance      
Tensor Processing     Yes
Deep Learning (Tensor) Performance      
NVIDIA Tensor Cores     104
Integer Operations (INT8)      
Ray-Tracing
NVIDIA RT Cores     26
RTX-OPS      
Rays Cast      
Power & Thermals
Graphics Card Power Connectors      
Board Power     70 W
Minimum Recommended PSU      
Maximum GPU Temperature      
Physical
Form Factor     Dual Slot
Low Profile Compatible     No
Low Profile Support      
Dimensions     167.64 x 68.58 mm
Package Type     OEM