Nvidia announced today Nvidia RTX Pro Blackwell series – a brand new generation of workstation and server graphics processing units.
According to NVIDIA, the GPUS workflows for KI, technical, creative, technical and design specialists with accelerated computers, AI inference, Ray tracking and neural rendering technologies newly define. The company unveiled the news throughout the Keynote speech by Jensen Huang, CEO of Nvidia, on the GTC 2025 event.
For all the pieces, from agents -KI, simulation, prolonged reality, 3D design and complicated visual effects to the event of physical AI that develops autonomous robots, vehicles and intelligent rooms, the RTX Pro Blackwell series offers experts in industries with computing power, storage capability and data transparent directly on their desktop, from the desktop, on the prevention.
The recent line -up includes:
- GPU from data center: Nvidia RTX Pro 6000 Blackwell Server Edition
- Desktop GPUS: NVIDIA RTX Pro 6000 Blackwell Workstation Edition, Nvidia RTX
- Pro 6000 Blackwell Max-Q Workstation Edition, Nvidia RTX Pro 5000 Blackwell,
- NVIDIA RTX Pro 4500 Blackwell and Nvidia RTX Pro 4000 Blackwell
- Laptop GPUS: NVIDIA RTX Pro 5000 Blackwell, Nvidia RTX Pro 4000 Blackwell,
- NVIDIA RTX Pro 3000 Blackwell, Nvidia RTX Pro 2000 Blackwell, Nvidia RTX Pro
- 1000 Blackwell and Nvidia RTX Pro 500 Blackwell
“Software developers, data scientists, artists, designers and engineers need high-performance AI and graphic performance to exceed the borders of visual computer and simulation and tackle incredible industrial challenges,” said Bob Pette, Vice President of Enterprise Platforms at NVIDIA. “The introduction of Nvidia Blackwell in workstations and servers will tackle productivity, performance and speed at recent heights and speed up the AI inference, data science, visualization and content creating.”
The Nvidia Blackwell technology involves workstations and data centers
RTX Pro Blackwell GPUS unlock the potential of generative, agents and physical AI by delivering extraordinary performance, efficiency and scale.
NVIDIA RTX Pro Blackwell GPUS Feature:
- NVIDIA Streaming Multiprocessor: bietet bis zu 1,5-mal schneller Durchsatz und neue neuronale Shader, die KI in programmierbare Shader integrieren, um das nächste Jahrzehnt von Ai-Augmented-Grafik-Innovationen voranzutreiben.
- RT cores of the fourth generation: Deliver as much as two-time performance of the previous generation to create photoreal, physically accurate scenes and complicated 3D designs with optimizations for the Nvidia-RTX-MEGA geometry.
- Tensor Cores fifth generation: delivers as much as 4,000 AI billions per second and add support for FP4 precision and NVIDIA DLSS 4-multi-frame generation, which enables a brand new era of AI-powered graphics and the power to perform and protect larger AI models faster.
- Larger, faster GDDR7 memory: increases the bandwidth and capability – as much as 96 GB for workstations and servers and as much as 24 GB on laptops. In this manner, applications can run faster and work with larger, more complex data sets for all the pieces, from combating massive 3D and AI projects to the research of huge virtual realistic environments.
- Ninth generation NVIDIA NVENC: accelerates the video coding speed and improves the standard for skilled video applications with additional support for 4: 2: 2 coding.
- NVIDIA NVDEC of the sixth generation: offers as much as the double of the decoding throughput H.264 and offers support for 4: 2: 2 H.264 and HEVC decode. Experts can profit from high-quality video playback, speed up video data intake and use advanced AI-powered video editing functions.
- PCIe of the fifth generation: The support for the fifth generation PCI Express offers double bandwidth over the previous generation, improves the info transmission speeds from the CPU storage and the event of a faster performance for data intensive tasks.
- DisplayPort 2.1: Ride high-resolution displays at as much as 4K at 480 Hz and 8k at 165 Hz. An increased bandwidth enables seamless multi-monitor setups, while a high dynamics and better color depth support for tasks reminiscent of video editing, 3D design and live broadcasting provide more detailed color accuracy.
- Multi-instance GPU (MIG): The RTX Pro 6000 data center for data center and desktop GPUs and 5000-series desktop GPUS MIG technology, which enables protected partitioning of a single GPU in as much as 4 instances (6000 series) or two instances (5000 series).
According to NVIDIA, error insulation is designed to forestall the workload for protected, efficient resource project for various work loads and to maximise performance and adaptability.
The recent laptop GPUS also supports the most recent Nvidia Blackwell Max-Q technologies, which optimize the laptop performance and current efficiency with AI intelligently and repeatedly.
With neuronal rendering and AI Augusted tools, Nvidia RTX Pro Blackwell GPUS enables the creation of breathtaking graphics, digital twins of real environments and haunting experiences with unprecedented speed and efficiency. The GPUs are created for the rise in computer-aided 3D workflows for design and constructing information models, whereby designers and engineers offer an exceptional performance for complex modeling, rendering and visualization.
The RTX Pro 6000 Blackwell Server Edition was developed for the availability of Enterprise Data Center and has a passively chilled thermal design and could be configured with as much as eight GPUs per server. For workloads that require the calculation of the density and scale that supply data centers, the RTX Pro 6000 Blackwell Server Edition offers a strong performance for the following generation, scientific and visual computer applications in industries reminiscent of healthcare, manufacturing, retail and media and entertainment.
In addition, this powerful GPU can mix with NVIDIA VGPU software together of AI workloads in virtualized environments and supply high-performance virtual workstation instances for distant users. NVIDIA VGPU support for the NVIDIA RTX Pro 6000 Blackwell Server Edition GPU is predicted within the second half of this 12 months.
“Foster + Partners has the NVIDIA RTX Pro 6000 Blackwell Max-Q Workstation Edition GPU for Cyclops, our GPU-based Ray Tracing product,” said Martha Tsigkari, Head of Applied Research and Development and Senior Partner at Foster + Partners. “The recent Nvidia Blackwell GPU has managed to exceed all the pieces now we have tested beforehand. If, for instance, it has been used with cyclops, it has carried out the speed of Nvidia RTX A6000 GPUs at 5x. The rendering of speeds also increases five times, with tools reminiscent of Zyklops to get feedback with the method with the method with the Honor.
“Nvidia RTX Pro 6000 Blackwell Workstation Edition GPUs enable incredibly sharp and photo -realistic graphics,” said Jeff Hammoud, Chief Design Officer at Rivian. “In conjunction with a Varjo XR4 headset and Autodesk VRED, the system supplied that required for immersive reviews of automotive designs.
RTX Pro GPUs runs on the Nvidia AI platform and has a bigger storage capability and the most recent tensor cores to speed up a deep ecosystem of AI evaluation applications based on NVIDIA CUDA and RTX technology. With all the pieces that the most recent tools for AI-based content creating and recent argumentation models reminiscent of the Nvidia Llama Nemotron Reason models family and Nvidia Nim Microservices presented today is quicker than ever. With over 400 Nvidia-Cuda-X libraries, developers can easily create, optimize, provide and scale recent AI applications, from workstations to the info center or the cloud.
Companies can quickly pursue their AI development and detration by getting access to an easy-to-use inference microservices with a Nvidia RTX Pro GPU and the Nvidia Omniverse and the Nvidia-AI company platforms, the Nvidia blueprints and Nvidia-Nims. You can even perform these applications in the last word universal data center GPU for AI and visual computing on a scale, whereby the groundbreaking acceleration for essentially the most demanding computing-intensive corporate workloads with the RTX Pro 6000 Blackwell Server Edition.
Availability
The NVIDIA RTX Pro 6000 Blackwell Server Edition will soon be available in server configurations by leading Data Center system partners reminiscent of Cisco, Dell Technologies, Hewlett Packard Enterprise, Lenovo and Supermicro.
Cloud service provider and GPU -Cloud provider reminiscent of AWS, Google Cloud, Microsoft Azure and CoreWeave will probably be among the many first to be driven by the NVIDIA RTX Pro 6000 Blackwell Server Edition in the midst of this 12 months. In addition, the Server Edition GPU will probably be available in data center platforms from Asus, Gigabyte, Ingrasys, Quanta Cloud Technology (QCT) and other global system partners.
The NVIDIA RTX Pro 6000 Blackwell Workstation Edition and the NVIDIA RTX Pro 6000 Blackwell Max-Q Workstation Edition will probably be available from April via global sales partners reminiscent of Pny and TD-Synex with availability of manufacturers reminiscent of Boxx, Dell, HP Inc., Lambda and Lenovo, from May.
The NVIDIA RTX Pro 5000, RTX Pro 4500 and RTX Pro 4000 Blackwell GPUS will probably be available in summer by Boxx, Dell, HP and Lenovo in addition to global sales partners.
Nvidia RTX Pro Blackwell Laptop GPUS will probably be available from Dell, HP, Lenovo and Razer from this 12 months.
