NVIDIA Unveils Powerful Blackwell RTX PRO GPUs for AI and Graphics Workloads

Where AI and Graphics Converge: NVIDIA Blackwell Universal Data Center GPU Accelerates Demanding Enterprise Workloads

NVIDIA RTX PRO 6000 Blackwell Server Edition delivers groundbreaking capabilities for diverse applications, including multimodal AI inference, immersive content creation and scientific computing. The first NVIDIA Blackwell-powered data center GPU built for both enterprise AI and visual computing -- the NVIDIA RTX PRO 6000 Blackwell Server Edition -- is designed to accelerate the most demanding AI and graphics applications for every industry. Compared to the previous-generation NVIDIA Ada Lovelace architecture L40S GPU, the RTX PRO 6000 Blackwell Server Edition GPU will deliver a multifold increase in performance across a wide array of enterprise workloads -- up to 5x higher large language model (LLM) inference throughput for agentic AI applications, nearly 7x faster genomics sequencing, 3.3x speedups for text-to-video generation, nearly 2x faster inference for recommender systems and over 2x speedups for rendering. It's part of the NVIDIA RTX PRO Blackwell series of workstation and server GPUs announced today at NVIDIA GTC, the global AI conference taking place through Friday, March 21, in San Jose, California. The RTX PRO lineup includes desktop, laptop and data center GPUs that support AI and creative workloads across industries. With the RTX PRO 6000 Blackwell Server Edition, enterprises across various sectors -- including architecture, automotive, cloud services, financial services, game development, healthcare, manufacturing, media and entertainment and retail -- can enable breakthrough performance for workloads such as multimodal generative AI, data analytics, engineering simulation, and visual computing. Content creation, semiconductor manufacturing and genomics analysis companies are already set to harness its capabilities to accelerate compute-intensive, AI-enabled workflows. Universal GPU Delivers Powerful Capabilities for AI and Graphics The RTX PRO 6000 Blackwell Server Edition packages powerful RTX AI and graphics capabilities in a passively cooled form factor designed to run 24/7 in data center environments. With 96GB of ultrafast GDDR7 memory and support for Multi-Instance GPU, or MIG, each RTX PRO 6000 can be partitioned into as many as four fully isolated instances with 24GB each to run simultaneous AI and graphics workloads. RTX PRO 6000 is the first universal GPU to enable secure AI with NVIDIA Confidential Computing, which protects AI models and sensitive data from unauthorized access with strong, hardware-based security -- providing a physically isolated trusted execution environment to secure the entire workload while data is in use. To support enterprise-scale deployments, the RTX PRO 6000 can be configured in high-density accelerated computing platforms for distributed inference workloads -- or used to deliver virtual workstations with NVIDIA vGPU software to power AI development and graphics-intensive applications. The RTX PRO 6000 GPU delivers supercharged inferencing performance across a broad range of AI models and accelerates real-time, photorealistic ray tracing of complex virtual environments. It includes the latest Blackwell hardware and software innovations like fifth-generation Tensor Cores, fourth-generation RT Cores, DLSS 4, a fully integrated media pipeline and second-generation Transformer Engine with support for FP4 precision. Enterprises can run the NVIDIA Omniverse and NVIDIA AI Enterprise platforms at scale on RTX PRO 6000 Blackwell Server Edition GPUs to accelerate the development and deployment of agentic and physical AI applications, such as image and video generation, LLM inference, recommender systems, computer vision, digital twins and robotics simulation. Accelerated AI Inference and Visual Computing for Any Industry Black Forest Labs, creator of the popular FLUX image generation AI, aims to develop and optimize state-of-the-art text-to-image models using RTX PRO 6000 Server Edition GPUs. "With the powerful multimodal inference capabilities of the RTX PRO 6000 Server Edition, our customers will be able to significantly reduce latency for image generation workflows," said name, title at Black Forest Labs. "We anticipate that, with the server edition GPUs' support for FP4 precision, our Flux models will run faster, enabling interactive, AI-accelerated content creation." Cloud graphics company OTOY will optimize its OctaneRender real-time rendering application for NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs. "The new NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs unlock brand-new workflows that were previously out of reach for 3D content creators," said Jules Urbach, CEO of OTOY and founder of the Render Network. "With 96 GB of VRAM, the new server-edition GPUs can run complex neural rendering models within OctaneRender's GPU path-tracer, enabling artists to tap into incredible new features and tools that blend the precision of traditional CGI augmented with frontier generative AI technology." Semiconductor equipment manufacturer KLA plans to use the RTX PRO 6000 Blackwell Server Edition to accelerate inference workloads powering the wafer manufacturing process -- the creation of thin discs of semiconductor materials that are core to integrated circuits. KLA and NVIDIA have worked together since 2008 to advance KLA's physics-based AI with optimized high-performance computing solutions. KLA's industry-leading inspection and metrology systems capture and process images by running complex AI algorithms at lightning-fast speeds to find the most critical semiconductor defects. "Based on early results, we expect great performance from the RTX PRO 6000 Blackwell Server Edition," said Kris Bhaskar, senior fellow and vice president of AI initiatives at KLA. "The increased memory capacity, FP4 reduced precision and new computational capabilities of NVIDIA Blackwell are going to be particularly helpful to KLA and its customers." Boosting Genomics and Drug Discovery Workloads The RTX PRO 6000 Blackwell Server Edition also demonstrates game-changing acceleration for genomic analysis and drug discovery inference workloads, enabled by a new class of dynamic programming instructions. On a single RTX PRO 6000 Blackwell Server Edition GPU, Fastq2bam and DeepVariant -- elements of the NVIDIA Parabricks pipeline for germline analysis -- run up to 1.5x faster compared with using an L40S GPU, and 1.75x faster compared with using an NVIDIA H100 GPU. For Smith-Waterman, a core algorithm used in many sequence alignment and variant calling applications, RTX PRO 6000 Blackwell Server Edition GPUs accelerate throughput up to 6.8x compared with L40S GPUs. And for OpenFold2, an AI model that predicts protein structures for drug discovery research, RTX PRO 6000 Blackwell Server Edition GPUs boost inference performance by up to 4.8x compared with L40S GPUs. Genomics company Oxford Nanopore Technologies is collaborating with NVIDIA to bring the latest AI and accelerated computing technologies to its sequencing systems. "The NVIDIA Blackwell architecture will help us drive the real-time sequencing analysis of anything, by anyone, anywhere," said Chris Seymour, vice president of advanced platform development at Oxford Nanopore Technologies. "With the RTX PRO 6000 Blackwell Server Edition, we have seen up to a 2x improvement in basecalling speed across our Dorado platform." Availability via Global Network of Cloud Providers and System Partners Platforms featuring the RTX PRO 6000 Blackwell Server Edition will be available from a global ecosystem of partners starting in May. AWS, Google Cloud, Microsoft Azure, IBM Cloud, CoreWeave, Crusoe, Lambda, Nebius and Vultr will be among the first cloud service providers and GPU cloud providers to offer instances featuring the RTX PRO 6000 Blackwell Server Edition. Cisco, Dell Technologies, Hewlett Packard Enterprise, Lenovo and Supermicro are expected to deliver a wide range of servers featuring the RTX PRO 6000 Blackwell Server Edition, as are Advantech, Aetina, Aivres, ASRockRack, ASUS, Compal, Foxconn, GIGABYTE, Inventec, MSI, Pegatron, Quanta Cloud Technology (QCT), MiTAC Computing, NationGate, Wistron and Wiwynn. To learn more about the NVIDIA RTX PRO Blackwell series and other advancements in AI, watch the GTC keynote by NVIDIA founder and CEO Jensen Huang:

Accelerating AI Development With NVIDIA RTX PRO Blackwell Series GPUs and NVIDIA NIM Microservices for RTX

A new line of professional-grade GPUs and AI-powered developers tools on PCs and workstations unveiled at NVIDIA GTC -- plus, the ChatRTX update now supports NVIDIA NIM, RTX Remix comes out of beta and this month's NVIDIA Studio Driver is available for download today. As generative AI capabilities expand, NVIDIA is equipping developers with the tools to seamlessly integrate AI into creative projects, applications and games to unlock groundbreaking experiences on NVIDIA RTX AI PCs and workstations. At the NVIDIA GTC global AI conference this week, NVIDIA introduced the NVIDIA RTX PRO Blackwell series, a new generation of workstation and server GPUs built for complex AI-driven workloads, technical computing and high-performance graphics. Alongside the new hardware, NVIDIA announced a suite of AI-powered tools, libraries and software development kits designed to accelerate AI development on PCs and workstations. With NVIDIA CUDA-X libraries for data science, developers can significantly accelerate data processing and machine learning tasks, enabling faster exploratory data analysis, feature engineering and model development with zero code changes. And with NVIDIA NIM microservices, developers can more seamlessly build AI assistants, productivity plug-ins and advanced content-creation workflows with peak performance. AI at the Speed of NIM With RTX PRO Series GPUs The RTX PRO Blackwell series is built to handle the most demanding AI-driven workflows, powering applications like AI agents, simulation, extended reality, 3D design and high-end visual effects. Whether for designing and engineering complex systems or creating sophisticated and immersive content, RTX PRO GPUs deliver the performance, efficiency and scalability professionals need. The new lineup includes: As AI and data science evolve, the ability to rapidly process and analyze massive datasets will become a key differentiator to enable breakthroughs across industries. NVIDIA CUDA-X libraries, built on CUDA, is a collection of libraries that deliver dramatically higher performance compared with CPU-only alternatives. With cuML 25.02 -- now available in open beta -- data scientists and researchers can accelerate scikit-learn, UMAP and HDBSCAN algorithms with zero code changes, unlocking new levels of performance and efficiency in machine learning tasks. This release extends the zero-code-change acceleration paradigm established by cuDF-pandas for DataFrame operations to machine learning, reducing iterations from hours to seconds. Optimized AI software unlocks even greater possibilities. NVIDIA NIM microservices are prepackaged, high-performance AI models optimized across NVIDIA GPUs, from RTX-powered PCs and workstations to the cloud. Developers can use NIM microservices to build AI-powered app assistants, productivity tools and content-creation workflows that seamlessly integrate with RTX PRO GPUs. This makes AI more accessible and powerful than ever. NIM microservices integrate top community and NVIDIA-built models, spanning capabilities and modalities important for PC and workstation use cases, including large language models (LLMs), images, speech and retrieval-augmented generation (RAG). Announced at the CES trade show in January, NVIDIA AI Blueprints are advanced AI reference workflows built on NVIDIA NIM. With AI Blueprints, developers can create podcasts from PDF documents, generate stunning 4K images controlled and guided by 3D scenes, and incorporate digital humans into AI-powered use cases. Coming soon to build.nvidia.com, the blueprints are extensible and provide everything needed to build and customize them for different use cases. These resources include source code, sample data, a demo application and documentation. From cutting-edge hardware to optimized AI models and reference workflows, the RTX PRO series is redefining AI-powered computing -- enabling professionals to push the limits of creativity, productivity and innovation. Learn about all the GTC announcements and the RTX PRO Blackwell series GPUs for laptops and workstations. Create NIMble AI Chatbots With ChatRTX AI-powered chatbots are changing how people interact with their content. ChatRTX is a demo app that personalizes a LLM connected to a user's content, whether documents, notes, images or other data. Using RAG, the NVIDIA TensorRT-LLM library and RTX acceleration, a user can query a custom chatbot to get contextually relevant answers. And because it all runs locally on Windows RTX PCs or RTX PRO workstations, they get fast and private results. Today, the latest version of ChatRTX introduces support for NVIDIA NIM microservices, giving users access to new foundational models. NIM is expected to soon be available in additional top AI ecosystem apps. Download ChatRTX today. Game On Half-Life 2 owners can now download a free Half-Life 2 RTX demo from Steam, built with RTX Remix and featuring the latest neural rendering enhancements. RTX Remix supports a host of AI tools, including NVIDIA DLSS 4, RTX Neural Radiance Cache and the new community-published AI model PBRFusion 3, which upscales textures and generates high-quality normal, roughness and height maps for physically based materials. The March NVIDIA Studio Driver is also now available for download, supporting recent app updates including last week's RTX Remix launch. For automatic Studio Driver notifications, download the NVIDIA app. In addition, NVIDIA RTX Kit, a suite of neural rendering technologies for game developers, is receiving major updates with Unreal Engine 5 support for the RTX Mega Geometry and RTX Hair features. Learn more about the NVIDIA RTX PRO Blackwell GPUs by watching a replay of NVIDIA founder and CEO Jensen Huang's GTC keynote and register to attend sessions from NVIDIA and industry leaders at the show, which runs through March 21.

NVIDIA Blackwell Powers Real-Time AI for Entertainment Workflows

RTX PRO Blackwell GPU series advances intelligent content creation, hyper-personalized media and live video pipelines. AI has been shaping the media and entertainment industry for decades, from early recommendation engines to AI-driven editing and visual effects automation. Real-time AI -- which lets companies actively drive content creation, personalize viewing experiences and rapidly deliver data insights -- marks the next wave of that transformation. With the NVIDIA RTX PRO Blackwell GPU series, announced yesterday at the NVIDIA GTC global AI conference, media companies can now harness real-time AI for media workflows with unprecedented speed, efficiency and creative potential. NVIDIA Blackwell serves as the foundation of NVIDIA Media2, an initiative that enables real-time AI by bringing together NVIDIA technologies -- including NVIDIA NIM microservices, NVIDIA AI Blueprints, accelerated computing platforms and generative AI software -- to transform all aspects of production workflows and experiences, starting with content creation, streaming and live media. Powering Intelligent Content Creation Accelerated computing enables AI-driven workflows to process massive datasets in real time, unlocking faster rendering, simulation and content generation. NVIDIA RTX PRO Blackwell GPUs series include new features that enable unprecedented graphics and AI performance. The NVIDIA Streaming Multiprocessor offers up to 1.5x faster throughput over the NVIDIA Ada generation, and new neural shaders that integrate AI inside of programmable shaders for advanced content creation. Fourth-generation RT Cores deliver up to 2x the performance of the previous generation, enabling the creation of massive photoreal and physically accurate animated scenes. Fifth-generation Tensor Cores deliver up to 4,000 AI trillion operations per second and add support for FP4 precision. And up to 96GB of GDDR7 memory boosts GPU bandwidth and capacity, allowing applications to run faster and work with larger, more complex datasets for massive 3D and AI projects, large-scale virtual-reality environments and more. "One of the most exciting aspects of new technology is how it empowers our artists with tools to enhance their creative workflows," said Steve May, chief technology officer of Pixar Animation Studios. "With Pixar's next-generation renderer, RenderMan XPU -- optimized for the NVIDIA Blackwell platform -- 99% of Pixar shots can now fit within the 96GB of memory on the NVIDIA RTX PRO 6000 Blackwell GPUs. This breakthrough will fundamentally improve the way we make movies." "Our artists were frequently maxing out our 48GB cards with ILM StageCraft environments and having to battle performance issues on set for 6K and 8K real-time renders," said Stephen Hill, principal rendering engineer at Lucasfilm. "The new NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition GPU lifts these limitations -- we're seeing upwards of a 2.5x performance increase over our current production GPUs, and with 96GB of VRAM we now have twice as much memory to play with." In addition, neural rendering with NVIDIA RTX Kit brings cinematic-quality ray tracing and AI-enhanced graphics to real-time engines, elevating visual fidelity in film, TV and interactive media. Including neural texture compression, neural shaders, RTX Global Illumination and Mega Geometry, RTX Kit is a suite of neural rendering technologies that enhance graphics for games, animation, virtual production scenes and immersive experiences. Fueling the Future of Streaming and Data Analytics Data analytics is transforming raw audience insights into actionable intelligence faster than ever. NVIDIA accelerated computing and AI-powered frameworks enable studios to analyze viewer behavior, predict engagement patterns and optimize content in real time, driving hyper-personalized experiences and smarter creative decisions. With the new GPUs, users can achieve real-time ingestion and data transformation with GPU-accelerated data loading and cleansing at scale. The NVIDIA technologies accelerating streaming and data analytics include a suite of NVIDIA CUDA-X data processing libraries that enable immediate insights from continuous data streams and reduce latency, such as: Along with cuML and cuDF, accelerated data science libraries provide seamless integration with the open-source Dask library for multi-GPU or multi-node clusters. NVIDIA RTX Blackwell PRO GPUs' large GPU memory can further assist with handling massive datasets and spikes in usage without sacrificing performance. And, the video search and summarization blueprint integrates vision language models and large language models and provides cloud-native building blocks to build video analytics, search and summarization applications. Breathing Life Into Live Media With NVIDIA RTX PRO Blackwell GPUs, broadcasters can achieve higher performance than ever in high-resolution video processing, real-time augmented reality and AI-driven content production and video analytics. New features include: "The NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition GPU is a transformative force in Cosm's mission to redefine immersive entertainment," said Devin Poolman, chief product and technology officer at Cosm, a global immersive technology, media and entertainment company. "With its unparalleled performance, we can push the boundaries of real-time rendering, unlocking the ultra-high resolution and fluid frame rates needed to make our live, immersive experiences feel nearly indistinguishable from reality." As a key component of Cosm's CX System 12K LED dome displays, RTX PRO 6000 Max-Q enables seamless merging of the physical and digital worlds to deliver shared reality experiences, enabling audiences to engage with sports, live events and cinematic content in entirely new ways. To learn more about NVIDIA Media2, watch the GTC keynote and register to attend sessions from NVIDIA and industry leaders at the show, which runs through Friday, March 21.

Nvidia launches Blackwell RTX Pro for workstations and servers

Nvidia said the GPUs redefine workflows for AI, technical, creative, engineering and design professionals with accelerated computing, AI inference, ray tracing and neural rendering technologies. The company unveiled the news during the keynote speech of Jensen Huang, CEO of Nvidia, at the GTC 2025 event. For everything from agentic AI, simulation, extended reality, 3D design and complex visual effects to developing physical AI powering autonomous robots, vehicles and smart spaces, the RTX Pro Blackwell series provides professionals across industries with compute power, memory capacity and data throughput right at their fingertips -- from their desktop, on the go with mobile workstations or powered by data center GPUs. The new lineup includes: "Software developers, data scientists, artists, designers and engineers need powerful AI and graphics performance to push the boundaries of visual computing and simulation, helping tackle incredible industry challenges," said Bob Pette, vice president of enterprise platforms at Nvidia, in a statement. "Bringing Nvidia Blackwell to workstations and servers will take productivity, performance and speed to new heights, accelerating AI inference serving, data science, visualization and content creation." Nvidia Blackwell technology comes to workstations and data centers RTX Pro Blackwell GPUs unlock the potential of generative, agentic and physical AI by delivering exceptional performance, efficiency and scale. Nvidia RTX Pro Blackwell GPUs feature: Nvidia said Fault isolation is designed to prevent workload interference for secure, efficient resource allocation for diverse workloads, maximizing performance and flexibility. The new laptop GPUs also support the latest Nvidia Blackwell Max-Q technologies, which intelligently and continually optimize laptop performance and power efficiency with AI. With neural rendering and AI-augmented tools, Nvidia RTX PRO Blackwell GPUs enable the creation of stunning visuals, digital twins of real-world environments and immersive experiences with unprecedented speed and efficiency. The GPUs are built to elevate 3D computer-aided design and building information model workflows, offering designers and engineers exceptional performance for complex modeling, rendering and visualization. Designed for enterprise data center deployments, the RTX PRO 6000 Blackwell Server Edition features a passively cooled thermal design and can be configured with up to eight GPUs per server. For workloads that require the compute density and scale that data centers offer, the RTX PRO 6000 Blackwell Server Edition delivers powerful performance for next-generation AI, scientific and visual computing applications across industries such as healthcare, manufacturing, retail and media and entertainment. In addition, this powerful data center GPU can be combined with Nvidia vGPU software to power AI workloads across virtualized environments and deliver high-performance virtual workstation instances to remote users. Nvidia vGPU support for the Nvidia RTX PRO 6000 Blackwell Server Edition GPU is expected in the latter half of this year. "Foster + Partners has tested the Nvidia RTX PRO 6000 Blackwell Max-Q Workstation Edition GPU on Cyclops, our GPU-based ray-tracing product," said Martha Tsigkari, head of applied research and development and senior partner at Foster + Partners, in a statement. "The new Nvidia Blackwell GPU has managed to outperform everything we have tested before. For example, when using it with Cyclops, it has performed at 5x the speed of Nvidia RTX A6000 GPUs. Rendering speeds also increased five times, allowing tools like Cyclops to provide feedback on how well our design solutions perform in real time as we design them and resulting in intuitive yet informed decision-making from early conceptual stages." "Nvidia RTX PRO 6000 Blackwell Workstation Edition GPUs enable incredibly sharp and photorealistic graphics," said Jeff Hammoud, chief design officer at Rivian. "In conjunction with a Varjo XR4 headset and Autodesk VRED, the system delivered the level of crispness necessary for immersive automotive design reviews. With Nvidia Blackwell support for PCIe Gen 5, we used two powerful 600W GPUs via VR SLI, allowing us to achieve the highest pixel density and the most stunning visuals we have ever experienced in VR." RTX PRO GPUs run on the Nvidia AI platform and feature larger memory capacity and the latest Tensor Cores to accelerate a deep ecosystem of AI-accelerated applications built on Nvidia CUDA and RTX technology. With everything from the latest AI-based content creation tools and new reasoning models, such as the Nvidia Llama Nemotron Reason family of models and Nvidia NIM microservices unveiled today, inferencing is faster than ever. And with over 400 Nvidia CUDA-X libraries, developers can easily build, optimize, deploy and scale new AI applications, from workstations to the data center or cloud. Enterprises can fast-track their AI development and deployments by prototyping locally with an Nvidia RTX PRO GPU and the Nvidia Omniverse and Nvidia AI Enterprise platforms, Nvidia Blueprints and Nvidia NIM, which gives access to easy-to-use inference microservices backed by enterprise-level support. They can also run these applications at scale on the ultimate universal data center GPU for AI and visual computing, delivering breakthrough acceleration for the most demanding compute-intensive enterprise 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 from leading data center system partners including Cisco, Dell Technologies, Hewlett Packard Enterprise, Lenovo and Supermicro. Cloud service providers and GPU cloud providers including AWS, Google Cloud, Microsoft Azure and CoreWeave will be among the first to offer instances powered by the Nvidia RTX Pro 6000 Blackwell Server Edition later this year. In addition, the server edition GPU will 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 Nvidia RTX PRO 6000 Blackwell Max-Q Workstation Edition will be available through global distribution partners such as PNY and TD Synnex starting in April, with availability from manufacturers, such as BOXX, Dell, HP Inc., Lambda and Lenovo, starting in May. The Nvidia RTX PRO 5000, RTX PRO 4500 and RTX PRO 4000 Blackwell GPUs will be available in the summer from Boxx, Dell, HP and Lenovo and through global distribution partners. Nvidia RTX PRO Blackwell laptop GPUs will be available from Dell, HP, Lenovo and Razer starting later this year.

Nvidia GTC 2025: New Blackwell Ultra GPU series is the most powerful AI hardware yet

There's also a new Nvidia RTX PRO 6000 Blackwell Server Edition designed for enterprise workloads Nvidia has taken the wraps off its latest Blackwell Ultra flagship GPU hardware as it looks to assert its place as the global leader in AI computing. Revealed at its Nvidia GTC event in San Jose, the new Blackwell Ultra hardware offers more power and efficiency in the data center than previous generations as the company looks to establish itself as the backbone of future AI development and deployment. Declaring it to be "built for the age of AI reasoning", Nvidia says Blackwell Ultra can help democratize AI adoption across the world, making it possible for more organizations to enjoy the benefits such compute can bring. Nvidia noted that the rapid growth of AI use cases around the world in the past few years has led for a huge demand for compute, as businesses and consumers alike clamour for more. "AI has made a giant leap -- reasoning and agentic AI demand orders of magnitude more computing performance," said Jensen Huang, founder and CEO of NVIDIA. "We designed Blackwell Ultra for this moment -- it's a single versatile platform that can easily and efficiently do pretraining, post-training and reasoning AI inference." The increase in reasoning models in particular has led for a boom in requirements for a full-stack offering that is cost-effective but also gets the job done. Built on the initial Blackwell architecture unveiled at GTC 2024, Blackwell Ultra will offer 1.5x more FP4 inference, and are set to be available ind evices built by Nvidia partners in the second half of 2025. It will be present in a host of new offerings from Nvidia, including the upgraded GB300 NVL72 rack, which it says offers improved energy efficiency and serviceability, with bandwidth speeds of up to 130Tb/s. However that wasn't all when it comes to new Blackwell hardware, as the company also revealed the Nvidia RTX PRO 6000 Blackwell Server Edition, designed for enterprise workloads such as multimodal AI inference, immersive content creation and scientific computing. Nvidia says the new release offers huge advances on the previous-generation Ada Lovelace architecture L40S GPU, providing up to 5x higher LLM inference throughput for agentic AI applications, nearly 7x faster genomics sequencing, 3.3x speedups for text-to-video generation, nearly 2x faster inference for recommender systems and over 2x speedups for rendering. Each RTX PRO 6000 can also be partitioned into as many as four fully isolated instances with 24GB each to run simultaneous AI and graphics workloads, with 96GB of ultrafast GDDR7 memory and support for multi-instance GPU. They can also be configured in high-density accelerated computing platforms for distributed inference workloads -- or used to deliver virtual workstations using Nvidia vGPU software, for graphics-intensive applications or to power AI development. "With the RTX PRO 6000 Blackwell Server Edition, enterprises across various sectors -- including architecture, automotive, cloud services, financial services, game development, healthcare, manufacturing, media and entertainment and retail -- can enable breakthrough performance for workloads such as multimodal generative AI, data analytics, engineering simulation, and visual computing," noted Nvidia's Sandeep Gupte.

Nvidia's RTX Pro 6000 Blackwell GPU Is Very Powerful and Power-Hungry

Nvidia announced a new series of professional-grade GPUs and AI-powered tools for PCs and workstations. The RTX Pro Blackwell series GPUs are designed for demanding professional designers, creatives, and developers. The Nvidia RTX Pro 6000 Blackwell desktop GPU ships with 96GB of speed GDDR7 memory. It is power-hungry, requiring 600 watts, even more than the RTX 5090's thirsty 575-watt demands. As The Verge notes, there are other similarities between the Pro 6000 and the RTX 5090, as both GPus have double flow-through cooling, 1,792 GB/s memory bandwidth, and 24,064 CUDA cores. Alongside the top-of-the-line RTX Pro 6000 Blackwell, Nvidia also unveiled RTX Pro 5000 Blackwell, RTX Pro 4500 Blackwell, and RTX Pro 4000 Blackwell GPUs for desktop workstations, plus RTX Pro Blackwell GPUs for laptops in 5000, 4000, 3000, 2000, 1000, and 500-series configurations. "Software developers, data scientists, artists, designers and engineers need powerful AI and graphics performance to push the boundaries of visual computing and simulation, helping tackle incredible industry challenges," says Bob Pette, vice president of enterprise platforms at Nvidia. "Bringing Nvidia Blackwell to workstations and servers will take productivity, performance and speed to new heights, accelerating AI inference serving, data science, visualization and content creation." Although specific performance metrics vary by GPU, Nvidia says that all its RTX Pro Blackwell GPUs feature a streaming multiprocessor that is up to 1.5 times faster than prior comparable Blackwell GPUs, fourth-generation RT cores that are twice as fast, fifth-generation tensor cores, faster GDDR7 memory, and improved codecs. For high-end video work, H.264 decoding is up to twice as fast on the latest GPUs. "Professionals can benefit from high-quality video playback, accelerate video data ingestion, and use advanced AI-powered video editing features," Nvidia explains. Further, the new Blackwell GPUs offer fifth-generation PCIe support, which doubles the bandwidth over the previous generation, and DisplayPort 2.1 support. DisplayPort 2.1 can drive high-resolution 4K displays at up to 480Hz and 8K at 165Hz. This standard also offers high color bit depth support, which can impact professional video editing tasks. At the high end of the lineup, the RTX Pro 6000 data center and desktop GPUs, plus the 5000 series desktop GPUs, feature multi-instance GPU (MIG) support. This enables users to partition a single GPU into up to four (6000 series) or two (5000 series) instances. This can diversify workloads and maximize workflow flexibility in certain use cases. On the laptop side of things, the new laptop GPUs utilize the latest Nvidia Blackwell Max-Q technologies to optimize performance and efficiency depending on the situation. The new Nvidia RTX Pro Blackwell chips will be available later this year. They will be included in products from Nvidia partners, including Dell, HP, Lenovo, and Razer, later this year as well.

NVIDIA Blackwell RTX PRO Comes to Workstations and Servers for Designers, Developers, Data Scientists and Creatives to Build and Collaborate With Agentic AI

GTC -- NVIDIA today announced the NVIDIA RTX PRO™ Blackwell series -- a revolutionary generation of workstation and server GPUs redefining workflows for AI, technical, creative, engineering and design professionals with breakthrough accelerated computing, AI inference, ray tracing and neural rendering technologies. For everything from agentic AI, simulation, extended reality, 3D design and complex visual effects to developing physical AI powering autonomous robots, vehicles and smart spaces, the RTX PRO Blackwell series provides professionals across industries the latest and greatest compute power, memory capacity and data throughput right at their fingertips -- from their desktop, on the go with mobile workstations or powered by data center GPUs. The new lineup includes: "Software developers, data scientists, artists, designers and engineers need powerful AI and graphics performance to push the boundaries of visual computing and simulation, helping tackle incredible industry challenges," said Bob Pette, vice president of enterprise platforms at NVIDIA. "Bringing NVIDIA Blackwell to workstations and servers will take productivity, performance and speed to new heights, accelerating AI inference serving, data science, visualization and content creation." NVIDIA Blackwell Technology Comes to Workstations and Data Centers RTX PRO Blackwell GPUs unlock the potential of generative, agentic and physical AI by delivering exceptional performance, efficiency and scale. NVIDIA RTX PRO Blackwell GPUs feature: The new laptop GPUs also support the latest NVIDIA Blackwell Max-Q technologies, which intelligently and continually optimize laptop performance and power efficiency with AI. With neural rendering and AI-augmented tools, NVIDIA RTX PRO Blackwell GPUs enable the creation of stunning visuals, digital twins of real-world environments and immersive experiences with unprecedented speed and efficiency. The GPUs are built to elevate 3D computer-aided design and building information model workflows, offering designers and engineers exceptional performance for complex modeling, rendering and visualization. Designed for enterprise data center deployments, the RTX PRO 6000 Blackwell Server Edition features a passively cooled thermal design and can be configured with up to eight GPUs per server. For workloads that require the compute density and scale that data centers offer, the RTX PRO 6000 Blackwell Server Edition delivers powerful performance for next-generation AI, scientific and visual computing applications across industries such as healthcare, manufacturing, retail and media and entertainment. In addition, this powerful data center GPU can be combined with NVIDIA vGPU™ software to power AI workloads across virtualized environments and deliver high-performance virtual workstation instances to remote users. NVIDIA vGPU support for the NVIDIA RTX PRO 6000 Blackwell Server Edition GPU is expected in the latter half of this year. "Foster + Partners has tested the NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition GPU on Cyclops, our GPU-based ray-tracing product," said Martha Tsigkari, head of applied research and development and senior partner at Foster + Partners. "The new NVIDIA Blackwell GPU has managed to outperform everything we have tested before. For example, when using it with Cyclops, it has performed at 5x the speed of NVIDIA RTX A6000 GPUs. Rendering speeds also increased 5x, allowing tools like Cyclops to provide feedback on how well our design solutions perform in real time as we design them and resulting in intuitive yet informed decision-making from early conceptual stages." "Early evaluation of the RTX PRO 6000 Blackwell technology by GE HealthCare's engineering team has found the potential for up to 2x GPU processing time improvement on reconstruction algorithms, which could lead to significant benefit to customers," said Rekha Ranganathan, senior executive and general manager of platforms and digital solutions at GE HealthCare. "NVIDIA RTX PRO 6000 Blackwell Workstation Edition GPUs enable incredibly sharp and photorealistic graphics," said Jeff Hammoud, chief design officer at Rivian. "In conjunction with a Varjo XR4 headset and Autodesk VRED, the system delivered the level of crispness necessary for immersive automotive design reviews. With NVIDIA Blackwell support for PCIe Gen 5, we used two powerful 600W GPUs via VR SLI, allowing us to achieve the highest pixel density and the most stunning visuals we have ever experienced in VR." "The 96GB memory and massive AI processing power in the NVIDIA RTX PRO 6000 Blackwell Workstation Edition GPU has boosted our productivity up to 3x with AI models like Llama 3.3-70B and Mixtral 8x7b, the NVIDIA Omniverse platform and industrial copilots," said Shaun Greene, director of industry solutions at SoftServe. "We've seen immediate performance improvements and, using workstations, can now handle AI workloads that were previously only possible in the cloud or on rack servers -- unlocking new possibilities for interactive demos and production workloads in retail, manufacturing and industrial edge applications." RTX PRO GPUs run on the NVIDIA AI platform and feature larger memory capacity and the latest Tensor Cores to accelerate a deep ecosystem of AI-accelerated applications built on NVIDIA CUDA and RTX technology. With everything from the latest AI-based content creation tools and new reasoning models, such as the NVIDIA Llama Nemotron Reason family of models and NVIDIA NIM™ microservices unveiled today, inferencing is faster than ever. And with over 400 NVIDIA CUDA-X™ libraries, developers can easily build, optimize, deploy and scale new AI applications, from workstations to the data center or cloud. Enterprises can fast-track their AI development and deployments by prototyping locally with an NVIDIA RTX PRO GPU and the NVIDIA Omniverse™ and NVIDIA AI Enterprise platforms, NVIDIA Blueprints and NVIDIA NIM, which gives access to easy-to-use inference microservices backed by enterprise-level support. They can also run these applications at scale on the ultimate universal data center GPU for AI and visual computing, delivering breakthrough acceleration for the most demanding compute-intensive enterprise 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 from leading data center system partners including Cisco, Dell Technologies, Hewlett Packard Enterprise, Lenovo and Supermicro. Cloud service providers and GPU cloud providers including AWS, Google Cloud, Microsoft Azure and CoreWeave will be among the first to offer instances powered by the NVIDIA RTX PRO 6000 Blackwell Server Edition later this year. In addition, the server edition GPU will 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 NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition will be available through global distribution partners such as PNY and TD SYNNEX starting in April, with availability from manufacturers, such as BOXX, Dell, HP Inc., Lambda and Lenovo, starting in May. The NVIDIA RTX PRO 5000, RTX PRO 4500 and RTX PRO 4000 Blackwell GPUs will be available in the summer from BOXX, Dell, HP and Lenovo and through global distribution partners. NVIDIA RTX PRO Blackwell laptop GPUs will be available from Dell, HP, Lenovo and Razer starting later this year. To learn more about the NVIDIA RTX PRO Blackwell GPUs, watch the GTC keynote and register to attend sessions from NVIDIA and industry leaders at the show, which runs through March 21. Plus, explore extended-reality demos running on RTX PRO Blackwell GPUs at the XR Pavilion at The Tech Interactive museum.