IT Creations Partners

NVIDIA RTX A6000 GPU - System Overview

Performance

RTX A6000 GPU side

Compared to the Nvidia Quadro RTX 8000 GPU offering 4608 CUDA cores, the NVIDIA RTX A6000 runs on the latest Ampere architecture and delivers more than twice the CUDA cores at 10,752. This GPU also supports 336 Tensor cores, 112 ROPs, and 84 RT cores. With this new architecture, the Nvidia A6000 can leverage 38.7 TFLOPS of single-precision performance, 75.6 TFLOPS of RT core performance, and 309.7 TFLOPS² of Tensor performance to address the most complex applications. With 28.3 billion transistors on Samsung’s 8nm process chip, the A6000 is up to 2x faster in ray tracing compared to the previous generation.

Memory

Under the hood, the RTX A6000 has 48GB of GDDR6 memory running at 2000 MHz with a 384-bit memory interface and error correcting code (ECC). ECC helps meet the uncompromised, accurate, and reliable standards for mission critical applications. Intended for professional workstations, this A6000 GPU operates with the base clock running at 1455 MHz and a boost clock of 1860 MHz. If systems need more power, users can deploy the 3rd generation NVLink bridge to link two A6000 cards together for a total of 96GB of memory.

RTX A6000 GPU ports

Features

The dual slot card is built on an 8nm manufacturing process, which supports the latest technological advancements. The Ampere architecture incorporates 2nd generation ray tracing engines to render complex professional models with physically accurate shadows and reflections. The GPU also supports PCIe Gen 4.0 technology for double the bandwidth and faster data-transfer speeds compared to PCIe Gen 3.0. To take on the most demanding 4K or 8K video encoding workloads, the 7th generation NVENC engine provides better encoding quality than software-based x264 encoders.

Summary

Designed for digital content creation, the NVIDIA RTX A6000 GPU offers nearly twice the performance of the RTX 8000 GPU. Built on the Ampere architecture, the GPU also supports new RT cores, Tensor cores, PCIe 4.0, and CUDA cores to deliver the best performance for creators and developers.

Check Availability

NVIDIA RTX A6000 GPU - Specifications

Memory
    GPU Memory: 48 GB GDDR6
  • Error-correcting code (ECC)
  • Memory Interface: 384-bit
  • Memory Bandwidth: Up to 768 GB/s
Cores
  • NVIDIA CUDA Cores: 10,752
Performance
  • Single-Precision: 40.0 TFLOPS
  • Double-Precision: 1,250 GFLOPS
  • Transistor Count: 28.3B
NVIDIA NVLink
  • 2-way low profile (2-slot and 3-slot bridges)
System Interface
  • PCI Express Gen 4 x 16
Power Consumption
  • Max Power Consumption: 300W
  • Suggested PSU: 700W
  • Power connector: 8-pin EPS
Form Factor
  • 4.4" H x 10.5" L
  • Dual slot, full height
Display Connectors
  • 4 x DisplayPort 1.4
Processors
  • Streaming Multiprocessors: 84
  • Fabrication Process: 8nm
Engine
    Graphics APIs

  • DirectX 12.2
  • Shader Model 6.5
  • OpenGL 4.6
  • OpenCL 2.0
  • Vulkan 1.2
  • CUDA 8.6
  • vGPU Software Support

  • NVIDIA GRID
  • NVIDIA Quadro Virtual Data Center Workstation
  • NVIDIA Virtual Compute Server

Check Availability

Get a quote for NVIDIA RTX A6000 GPU

If you know what you want but can't find the exact configuration you're looking for, have one of our knowledgeable sales staff contact you. Give us a list of the components you would like to incorporate into the system, and the quantities, if more than one. We will get back to you immediately with an official quote.

[email protected]