Unrivalled Performance in..
AI & Data Science
5x faster training with TF32 & hardware sparsity support
Multi-GPU Workflows
Up to 96GB combined memory & 112GB/s NVLink bandwidth
Graphics & Simulation
Double-speed FP32 & 2x power efficiency over Turing
Ray Tracing
2x faster throughput & concurrent ray tracing/shading/denoising
*compared to the A100.
NVIDIA RTX A6000
Pricing starts from $0.35/hour
Most Powerful NVIDIA RTX A6000 GPU
Blazing Performance and Efficiency
The NVIDIA RTX A6000 takes the Ampere architecture to new heights for professional graphics and simulation. With double-speed FP32 processing, 2X faster ray tracing, and boosted power efficiency in a dual-slot form factor, you can blaze through CAD, CAE, and photorealistic rendering workloads. Whether evaluating architectural designs, prototyping products virtually, or crafting complex 3D visuals, the NVIDIA A6000 delivers the uncompromising speed and accuracy you need without high power demands.
Cutting-edge AI and Data Science Capabilities
The NVIDIA RTX A6000 amps up AI and data science workflows thanks to major advances in Tensor Core technology. You get up to 5X faster training for deep learning models without any code changes, plus optimised inferencing throughput to accelerate deployed AI apps. This GPU also provides full support for large datasets and model parameters, with 48GB of ultra-fast GDDR6 memory that can scale to 96 GB with NVLink. Whether building neural networks, analysing big data, or exploring AI graphics techniques like DLSS, the NVIDIA A6000 has the latest NVIDIA innovations to supercharge your work.
Benefits of NVIDIA RTX A6000
Third-Generation NVLink
Connects two GPUs, doubling your performance and memory. Tackle massive rendering, AI, VR, and visual computing workloads with ease, thanks to up to 112 GB/s bandwidth and a new connector design for wider compatibility.
Third-Generation Tensor Cores
Train AI models 5x faster with TF32 precision. Hardware support for sparsity doubles inferencing throughput, while AI-powered features like DLSS, AI denoising, and enhanced editing bring AI directly to your graphics workflows.
NVIDIA Ampere Architecture-Based CUDA Cores
Experience double-speed processing for FP32 operations and up to 2x more power efficiency than previous generations. Witness significant performance gains across graphics and compute-intensive workloads like 3D model development and desktop simulation.
Second-Generation RT Cores
Render scenes with stunning realism up to 2x faster than before. Enjoy the flexibility of concurrent ray tracing with shading or denoising for faster workloads, and experience smoother, more accurate results with accelerated ray-traced motion blur.
PCI Express Gen 4.0
Get the full potential of your GPU with 2x the bandwidth of PCIe Gen 3.0. Enjoy faster data transfers from CPU memory for data-intensive tasks like AI and data science, and benefit from accelerated GPU DMA transfers for video and I/O operations.
Virtual Workstations
With virtual GPU (vGPU) software, get a personal workstation repurposed into multiple high-performance virtual workstation instances to share resources to drive high-end design, AI, and compute workloads.
Available on
Hyperstack
