Nvidia reportedly boosts Vera Rubin performance to ward hyperscalers off AMD Instinct AI accelerators — increased boost clocks and memory bandwidth pushes power demand by 500 watts to 2300 watts

Nvidia is reportedly enhancing the Vera Rubin AI datacenter platform to outperform AMD's Instinct AI accelerators, with increased boost clocks and memory bandwidth. The power demand for the Rubin GPU is said to rise by 500 watts to 2300 watts, aiming to deliver superior performance compared to its competitors. The power increase allows for improved real-world performance, sustained clocks, and enhanced throughput under heavy workloads. This boost in power also translates to higher system-level performance, potentially reducing the number of GPUs needed for tasks and improving overall efficiency for hyperscalers. Additionally, the higher TDP provides manufacturing benefits, such as improved yield and reliability for large-scale datacenter deployments.