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

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:

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 Laptop GPUs

Data center GPU: NVIDIA RTX PRO 6000 Blackwell Server Edition

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

LINK:	https://blogs.nvidia.com/blog/rtx-ai-garage-blackwell-pro-nim/...
	See more stories from nvidia

More from Nvidia