Nvidia has unveiled its next-generation AI chip platform, named "Rubin," set to be rolled out in 2026. The announcement, made by CEO Jensen Huang at the Computex trade show in Taipei, highlights Nvidia's commitment to advancing AI technology and maintaining its dominance in the AI chip market.
Nvidia's announcement of the Rubin platform is part of its goal to advance AI technology and meet the growing demand for high-performance AI hardware.1
By accelerating its release schedule from every two years to annually, Nvidia aims to maintain its dominance in the AI chip market, where it currently holds an estimated 80% market share.23
The introduction of the Rubin platform in 2026 represents a significant advancement in Nvidia's AI hardware, comprising new CPUs, GPUs, and networking chips designed to power AI applications with high-bandwidth memory from manufacturers like SK Hynix, Micron, and Samsung.14
The Rubin platform features new Versa CPUs and next-generation GPUs that bundle high-bandwidth memory from SK Hynix, Micron, and Samsung to power AI applications.12
Nvidia is focusing on improving power efficiency while enhancing the AI capabilities of its data center chips, which is crucial given the growing power demands of AI hardware.34
The Rubin R100 GPUs, expected to be mass-produced in late 2025, will use a 4x reticle design and TSMC's CoWoS-L packaging technology on the N3 process node, with systems like DGX and HGX solutions available in the first half of 2026.3
The Rubin R100 GPUs will leverage next-generation HBM4 DRAM, which is expected to be developed by Samsung and SK Hynix by 2025, offering up to 16-Hi stacks for enhanced performance.1
NVIDIA plans to utilize TSMC's advanced packaging technologies, such as CoWoS-L and SoIC, which will allow for larger reticle sizes (up to 5.5x by 2026) and increased HBM sites (up to 12) compared to current configurations.1
The GR200 Superchip module, housing two R100 GPUs and an upgraded Grace CPU based on TSMC's 3nm process, will further enhance the capabilities of the Rubin platform.1
Nvidia is collaborating with Microsoft to develop AI models integrated into Windows 11, providing developers with easy access to GPU-accelerated small language models (SLMs) for enhanced AI functionalities.1
The company aims to expand AI computing beyond data centers, targeting a broader customer base, including businesses and government agencies across various industries, by offering new tools and software models to facilitate AI integration.2
Nvidia is also integrating AI capabilities into gaming laptops, with brands like Asus and MSI set to release "RTX AI PC" laptops featuring up to GeForce RTX 4070 GPUs, supporting Microsoft's AI advancements and including Nvidia's RTX AI Toolkit for model optimization and deployment.1