%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
At the 2026 CES International Consumer Electronics Show in Las Vegas, AI leader NVIDIA officially launched its highly anticipated next-generation AI platform—Rubin. At the core of this platform, the new super chip Vera Rubin made its debut, marking another significant leap for NVIDIA in the field of high-performance computing.
According to AIbase, the Rubin platform is designed to provide more efficient computing power for current agent AI and large-scale reasoning models. The Vera Rubin chip features an innovative integrated design, packaging a Vera CPU and two Rubin GPUs in a single processor. Compared to the previous Blackwell architecture, the new platform has achieved a qualitative leap in efficiency. Official data from NVIDIA shows that when training the same mixture-of-experts model (MoE), the Rubin platform requires only a quarter of the number of GPUs needed previously.
In addition to the core chip, NVIDIA also showcased a range of network and storage components, including the NVLink6 switch and the ConnectX-9 super NIC. These technologies together form the Vera Rubin NVL72 server, capable of building large-scale supercomputing clusters.
For enterprises, the direct benefit brought by the new architecture is a significant reduction in costs. AIbase reported that the Rubin platform can reduce the cost of processing "tokens" during the AI inference stage by 90%. This means that when processing massive amounts of language, image, and video data, companies will see significant optimization in energy consumption and overall operational costs. Despite competition from Advanced Micro Devices (AMD) and tech giants like Google and Amazon developing their own chips, NVIDIA aims to continue solidifying its dominant position in the global AI computing market by maintaining a fast-paced product iteration cycle each year.
Key Points:
🚀 New Architecture Launch: NVIDIA officially launched the Rubin platform, which includes the Vera Rubin super chip with new CPU and GPU cores integrated.
📉 Significant Efficiency Improvement: Compared to previous products, the number of GPUs required to train similar AI models has been reduced by 75%, and the cost of inference has dropped by 90%.
🌐 Comprehensive Computing Solution: The new platform covers a complete ecosystem from switches to storage solutions, aiming to support complex AI model reasoning at the scale of trillions of parameters.