Ensuring water quality is critical to protecting the environment and human health. Accurate monitoring is essential. This study assessed the physicochemical and microbiological parameters of groundwater samples and utilized Artificial Intelligence (AI) based models, Support Vector Regression (SVR), Multi-Linear Regression (MLR), Random Forest (RF), XGBoost and CatBoost to predict water quality parameters from the experimental result. The groundwater samples were collected from various boreholes within three core urban local governments (Gwale, Tarauni and Nasarawa) and two peri-urban local governments (Kumbotso and Ungoggo). The pH, Electrical Conductivity (EC), Salinity, Turbidity (NTU), Cl−, Fe, SO42− and microbiological analysis were in accordance with WHO guidelines in some regions, and the limit in a few regions is below the limits. The models were trained, verified, and tested for their predictive performance ability, and their physicochemical prediction accuracy was compared by using each model’s observed data with the predicted data. The models showed high performance in both the training and validation stages, respectively. The Models can be utilized for future water quality prediction of groundwater and surface water while raising awareness among the public and industry on future water quality. Overall, our results have conclusively illustrated the prevalence of lower and elevated levels of physicochemical parameters in the majority of areas, surpassing the recommended values outlined by the World Health Organization (WHO) and National Environmental Quality Standards (NEQS) for drinking water.