RTX A2000│RTX A2000 12GB

NVIDIA RTX™ technology has fundamentally changed computer graphics, fusing the power of real-time ray tracing, AI, and advanced graphics and compute to drive the next wave of innovation in visual computing. The NVIDIA Ampere architecture is the second generation of NVIDIA RTX—delivering new levels of power and performance to professional workflows, accelerating time to decision, time to market, and time to solution.

The NVIDIA RTX A2000 │ RTX A2000 12GB brings the power of RTX to more professionals with a powerful low-profile, dual-slot GPU design, delivering real-time ray tracing, AI-accelerated compute, and high-performance graphics to your desktop. 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 up to 12GB of GDDR6 graphics memory with error correction code (ECC) support, another industry first in this segment. Design bigger, render faster, and work better with the NVIDIA RTX A2000 │ RTX A2000 12GB.

HD Gallery

  • DESCRIPTION
  • SPECIFICATION
  • BIOS / DRIVERS UPDATE
  • REQUIREMENT
►NVIDIA Ampere Architecture ►CUDA Cores
►Second Generation RT Cores ►Third-Generation Tensor Cores
►PCIe Gen 4 ►Higher Speed GDDR6 Memory
►Error Correcting Code (ECC) on Graphics Memory ►5th Generation NVDEC Enginei
►7th Generation NVENC Engine ►Graphics Preemption
►Compute Preemption ►NVIDIA RTX IO

GPU Architecture

NVIDIA Ampere Architecture

CUDA Parallel Processing cores

3,328

NVIDIA Tensor Cores

104

NVIDIA RT Cores

26

Single-Precision Performance1

8 TFLOPS

RT Core Performance1

15.6 TFLOPS

Tensor Performance1

63.9 TFLOPS2

GPU memory

6 GB GDDR6 with ECC | 12 GB GDDR with ECC

Memory Interface

192-bit

Memory Bandwidth

288 GB/s

Max Power Consumption

70 W

Graphics Bus

PCI Express 4.0 x 16

Display Connectors

mDP 1.4 (4)3

Form Factor

2.713”H x 6.6”L Dual Slot

Product Weight

294 g (Low Profile Bracket)
306 g (ATX Bracket)

Thermal Solution

Active

NVENC | NVDEC

1x | 1x (+AV1 decode)