Built from the ground up for enterprise AI, the NVIDIA DGX platform incorporates the best of NVIDIA software, infrastructure powered by the NVIDIA Rubin and NVIDIA Blackwell architectures, and expertise in a modern, unified AI development and training solution. Every aspect of the DGX platform is infused with NVIDIA AI expertise, featuring world-class software, record-breaking NVIDIA-accelerated infrastructure, and direct access to NVIDIA DGXperts to speed the ROI of AI for every enterprise.  

Infused With NVIDIA AI Expertise 

Every element in the DGX platform, from the engineering wonders within NVIDIA DGX SuperPOD to the full-stack, intelligent software in NVIDIA Mission Control, is infused with the AI expertise of NVIDIA. Our researchers have achieved AI breakthroughs using this platform for years and have completed millions of training runs with it. This vast institutional knowledge is incorporated directly into the design and evolution of the DGX platform, meaning the software tools and accelerated compute infrastructure you use today delivers the best of NVIDIA innovation and will keep getting better over time. 

NVIDIA DGX Software Stack  

• NVIDIA DGX SuperPOD: NVIDIA DGX SuperPOD is AI data center infrastructure that enables IT to deliver performance—without compromise—for every user and workload. As part of the NVIDIA DGX platform, DGX SuperPOD offers leadership class accelerated infrastructure and scalable performance for the most challenging AI workloads, with industry-proven results.
• NVIDIA DGX BasePOD: AI is powering mission-critical use cases in every industry—from healthcare to manufacturing to financial services. As part of the NVIDIA DGX platform, NVIDIA DGX BasePOD™ provides the critical foundation on which business transformation is realized and AI applications are born.
• NVIDIA Mission Control: NVIDIA Mission Control streamlines AI operations, from workloads to infrastructure, with world-class expertise delivered as software. It powers NVIDIA Blackwell data centers, bringing instant agility for inference and training while providing full-stack intelligence for infrastructure resilience. Every enterprise can run AI with hyperscale efficiency, simplifying and accelerating AI experimentation.

A Full Range of Accelerated Compute Options 

• NVIDIA DGX Vera Rubin NVL72: NVIDIA's most advanced liquid-cooled AI system, featuring a rack-scale design powered by NVIDIA Vera Rubin Superchips, purpose built to accelerate the world's most complex agentic AI and long-context reasoning models while maximizing cost-per-token.
• NVIDIA DGX GB300: Built with NVIDIA Grace Blackwell Superchips for AI training, post-training optimization, and test-time inference for complex AI models.
• NVIDIA DGX GB200: Leadership-class, liquid-cooled AI system featuring NVIDIA Grace Blackwell Superchips for today's leading-edge foundational model training and large-scale inference.
• NVIDIA DGX Rubin NVL8: Provides enterprises with a blueprint for success in the age of agentic AI, empowering AI pioneers to scale their operations without stumbling upon performance and efficiency bottlenecks. Built on the NVIDIA Rubin architecture, NVIDIA DGX Rubin NVL8 is purpose-built to accelerate training and inference for any AI workload.
• NVIDIA DGX B300: Powered by NVIDIA Blackwell Ultra GPUs, DGX B300 integrates seamlessly into data centers to accelerate training and real-time inference workloads.
• NVIDIA DGX B200: Unified AI system built with NVIDIA Blackwell for every stage of the AI pipeline, from training to fine-tuning to inference. DGX B200 is ideal for businesses looking for a single platform for all of their develop-to-deploy pipelines