Visit your regional NVIDIA website for local content, pricing, and where to buy partners specific to your country.
Performance for endless possibilities.
Find an NVIDIA design and visualization partner or shop the NVIDIA store.
Datasheet | Specs
The NVIDIA RTX™ 5000 Ada Generation GPU, powered by the NVIDIA Ada Lovelace architecture, unlocks breakthroughs in generative AI and delivers the performance required to meet the challenges of today’s professional workflows. With 100 third-generation RT Cores, 400 fourth-generation Tensor Cores, 12,800 CUDA® cores, and 32GB of graphics memory, the RTX 5000 excels in rendering, AI, graphics, and compute workload performance.
New RTX 5000 is a significant leap in performance over the previous generation, delivering next-gen capabilities for AI and 3D graphics workloads.
65.3 TFLOPS¹
151.0 TFLOPS¹
1,044.4 TFLOPS¹
1 Peak rates based on GPU Boost Clock.
2X the speed of the previous generation for single-precision floating-point (FP32) operations provides significant performance improvements for graphics and simulation workflows on the desktop, such as complex 3D computer-aided design (CAD) and computer-aided engineering (CAE).
With over 2X the throughput over the previous generation, third-generation RT Cores deliver massive speedups for workloads like photorealistic rendering of movie content, architectural design evaluations, and virtual prototyping of product designs. This technology also accelerates the rendering of ray-traced motion blur with greater visual accuracy.
Fourth-generation Tensor Cores deliver up to 4X the AI compute performance of the previous generation. These Tensor Cores support acceleration of the FP8 precision data type and provide independent floating-point and integer data paths to speed up execution of mixed floating-point and integer calculations.
With 32GB of GDDR6 memory, RTX 5000 gives data scientists, engineers, and creative professionals the GPU memory needed to work with large datasets and workloads like rendering, data analytics, and simulation.
Eighth-generation dedicated hardware encoder (NVENC) with AV1 encoding unlocks new opportunities for streamers, broadcasters, and video conferencing. It’s 40% more efficient than H.264, allowing users streaming at 1080p to increase their resolution to 1440p while running at the same bitrate and quality.
Support for NVIDIA RTX Virtual Workstation (vWS) software allows a personal workstation to be repurposed into multiple high-performance virtual workstation instances, letting remote users share resources to drive high-end design, AI, and compute workloads.
Unleash the true potential of creative workflows. With third-gen RT Cores and DLSS 3, RTX 5000 empowers artists and designers to work in real time, crafting photorealistic designs and simulations with complex geometry and high-resolution textures.
Be more productive and create more immersive experiences in any industry with generative AI. RTX 5000 accelerates compute-intensive AI workloads, delivering up to 2X higher inference performance over the previous generation, for rapid generation of high-quality images, videos, and 3D assets.
Experience a new era of AI-powered video content creation and streaming. With RTX 5000, harness the power of two encode and two decode engines combined with fourth-gen Tensor Cores to unlock limitless possibilities in AI video production and broadcast.
Accomplish compute-intensive data science tasks faster. With 32GB of GPU memory, the RTX 5000 makes it possible to interactively examine large datasets without cutting down the size of the data or reducing fidelity.
From ray tracing to physics simulation to neural graphics and generative AI, RTX 5000 is built to handle the demanding workloads of today’s industries. Delivering up to 3X higher performance than the previous generation, RTX 5000 helps you take your work to new heights.
3840x2160 resolution, SPECviewperf 2020 Siemens NX viewset tests.
1920x1080 resolution, Chaos V-Ray v5.0.
RTX 5000 Ada Generation vs RTX A5500 image generation, 512x512 Stable Diffusion webUI v1.3.1.
CUDA Toolkit 11.8 (cuBLAS performance), precision = INT8, input = zero.
NVIDIA Omniverse performance for real-time rendering at 4K with NVIDIA Deep Learning Super Sampling (DLSS) 3.
TensorRT, ResNet-50 V1.5 Inference, precision: mixed.
Performance testing with RTX 5000 Ada Generation and RTX A5500 GPUs and Intel Core i9-12900K. Performance based on pre-release build, subject to change.
Discover how Lake|Flato produced high-quality renders for their clients to experience in VR with an NVIDIA RTX 5000 Ada Generation.
Hotel Magdalena. Photography by Casey Dunn.
* Display ports are on by default for RTX 5000. Turn display ports off when using vGPU software. ** AI software and virtualization support for RTX 5000 will be available in an upcoming NVIDIA driver release, anticipated in Q3, 2023.
Intel and NVIDIA are ushering in the next generation of OEM workstation platforms. These new workstations, powered by the latest Intel Xeon W processors, NVIDIA RTX 6000 Ada Generation GPUs, and NVIDIA® ConnectX® smart network interface cards, are bringing unprecedented performance, features, and efficiency for creative and technical professionals.
Talk with an NVIDIA design and visualization partner or shop the NVIDIA store.
Talk to an NVIDIA product specialist about your professional needs.
Sign up for the latest news, updates, and more from NVIDIA.
NVIDIA Privacy Policy
* Display ports are on by default for RTX 5000. Turn display ports off when using virtual GPU (vGPU) software.