Rubin Superchips Launch: NVIDIA Powers the Future of Agentic and Large-Scale AI

NVIDIA  announced the launch of its Rubin platform, marking a major leap forward in AI infrastructure. Named in honor of pioneering astronomer Vera Rubin, the platform integrates six new chips—the NVIDIA Vera CPU, Rubin GPU, NVLink 6 Switch, ConnectX-9 SuperNIC, BlueField-4 DPU, and Spectrum-6 Ethernet Switch—to deliver one of the world’s most advanced AI supercomputers. Rubin aims to accelerate mainstream AI adoption while drastically reducing training and inference costs.

The Rubin platform leverages extreme codesign across hardware and software, providing up to 10x reduction in inference token cost and enabling the training of large-scale mixture-of-experts (MoE) models with 4x fewer GPUs compared with the NVIDIA Blackwell platform. Advanced innovations include NVIDIA NVLink interconnect technology, Transformer Engine, Confidential Computing, and the RAS Engine, all designed to optimize performance, security, and reliability.

Performance and Efficiency Breakthroughs

Rubin introduces next-generation AI-native infrastructure, including the NVIDIA Inference Context Memory Storage Platform, powered by BlueField-4. This enables scalable agentic AI reasoning with efficient data sharing and power-efficient performance. The platform’s Spectrum-X Ethernet Photonics switches deliver 5x improved power efficiency and uptime, while BlueField-4’s Advanced Secure Trusted Resource Architecture (ASTRA) ensures secure and isolated AI workloads.

The NVIDIA Vera Rubin NVL72 rack-scale system combines 72 Rubin GPUs and 36 Vera CPUs, offering unprecedented bandwidth and compute density, while the HGX Rubin NVL8 server supports x86-based generative AI workloads. NVIDIA DGX SuperPOD systems provide reference architecture for deploying Rubin at scale, integrating GPUs, CPUs, DPUs, networking, and management software.

Broad Ecosystem Adoption

The Rubin platform is already supported by major cloud providers, AI labs, and hardware partners. Early adopters include AWS, Google Cloud, Microsoft Azure, CoreWeave, Lambda, OCI, and xAI, while infrastructure partners such as Cisco, Dell, HPE, Lenovo, and Supermicro are building Rubin-powered servers. AI labs including OpenAI, Anthropic, Meta, Cohere, Mistral AI, and Perplexity plan to leverage Rubin for training advanced, large-context, multimodal models.

Industry Leaders React

• Jensen Huang, NVIDIA CEO: “Rubin arrives at exactly the right moment as AI computing demand skyrockets… it takes a giant leap toward the next frontier of AI.”
• Sam Altman, OpenAI: “The NVIDIA Rubin platform helps us scale AI progress so advanced intelligence benefits everyone.”
• Mark Zuckerberg, Meta: “Rubin promises the step-change in performance and efficiency required to deploy the most advanced models to billions.”
• Elon Musk, xAI: “Rubin will be a rocket engine for AI… NVIDIA remains the gold standard.”
• Satya Nadella, Microsoft: “With NVIDIA Vera Rubin GPUs, we will empower developers and organizations to create, reason, and scale in entirely new ways.”

Ecosystem and Software Collaboration

NVIDIA has expanded its partnership with Red Hat to deliver a complete AI stack optimized for Rubin, including Red Hat Enterprise Linux, OpenShift, and Red Hat AI, enabling Fortune 500 companies and AI innovators to deploy high-performance AI solutions efficiently.

Availability

Rubin-based products will be available through partners in the second half of 2026, offering a unified, secure, and scalable platform for AI training, inference, and agentic workloads. Microsoft will deploy Vera Rubin NVL72 systems in next-generation AI superfactories, while CoreWeave will integrate Rubin into its AI cloud platform to accelerate innovation across enterprise, research, and consumer applications.

With the Rubin platform, NVIDIA sets a new standard for AI infrastructure, combining unprecedented efficiency, scalability, and security to power the next generation of AI supercomputers and applications.