Nvidia: New Rubin Chips Progressing Smoothly, Helping to Accelerate AI Performance Summary Nvidia announced that the new "Rubin" data center products are upcoming, with significant performance improvements, training capabilities increased by 3.5 times compared to the previous generation, AI software running speed increased by 5 times, and lower operating costs. Companies like Microsoft will be the first to adopt this hardware. BlockBeats reports that on January 6, Nvidia (NVDA.O) announced that the highly anticipated new "Rubin" data center products will be launched later this year, allowing customers to test the technology and help accelerate the development of artificial intelligence. Nvidia stated that all six Rubin chips have been delivered from manufacturing partners and have passed several key tests, indicating that customer deployment is proceeding as planned. Its latest Rubin accelerator has a training performance 3.5 times higher than the previous Blackwell generation, and the speed of running AI software has increased 5 times. The company emphasizes that systems based on Rubin will have lower operating costs than those based on Blackwell because they use fewer components to achieve the same results. It is reported that Microsoft and other major remote computing service providers will be the first to adopt this new hardware in the second half of this year. (Jin10)