Transitioning to more intelligent, autonomous transportation systems necessitates network infrastructure capable of accommodating both substantial uplink traffic and massive vehicle connectivity. Current approaches addressing these throughput and connectivity requirements rely on the utilization of the multiple input, multiple output (MIMO) technology. However, When traditional linear detection/precoding processing methods are adopted, they require the deployment of an extensive number of co-located, access-point antennas to support a comparatively much smaller number of data streams. Such a setup significantly increases the power consumption on the radio side, raising substantial concerns about the operational costs and sustainability of such deployments, particularly in densely deployed scenarios, across extensive road networks. Addressing these concerns, this work proposes an Open Radio Access Network (Open-RAN) deployment that incorporates a Massively Parallelizable, Nonlinear (MPNL) MIMO processing framework and assesses, for the first time, its impact on the power consumption and vehicular connectivity in various Vehicle-to-Infrastructure (V2I) and Network (V2N) scenarios. We show that flexible, Open-RAN physical layer deployments, incorporating MPNL, emerge as a critical power efficiency enabler, especially when flexibly activating/deactivating employed RF elements. Our field-programmable gate array (FPGA) based evaluation of MPNL, reveals that it can lead to significant power savings on the radio side, by eliminating the need for a " massive " number of base station antennas and radio frequency (RF) chains. Additionally, our findings show substantial connectivity gains, exceeding 400%, in terms of concurrently transmitting vehicles compared to traditional processing approaches, without significantly affecting the access point power consumption budgets, thereby catalyzing the evolution towards more intelligent, fully autonomous, and sustainable transportation systems.