Information on "Memory Utilization (%)" for Nvidia as a company-wide, historical metric is not publicly available in its financial or operational reports. This metric is a real-time measure of the activity of an individual Graphics Processing Unit (GPU) and is not aggregated by Nvidia as a Key Performance Indicator (KPI) for the entire company.

The metric "memory utilization" refers to the percentage of time that the GPU's memory was being read from or written to during a specific sampling period. This data can be monitored on a single system using tools like nvidia-smi but is not tracked across all deployed GPUs globally.

While direct utilization data is unavailable, the demand for Nvidia's high-performance memory solutions, especially High-Bandwidth Memory (HBM) for AI applications, is a strong indicator of the critical role of memory in their products.