In hard milling, there has been a significant surge in demand for sustainable machining techniques. Research indicates that the Minimum Quantity Lubrication (MQL) method is a promising approach to achieving sustainability in milling processes due to its eco-friendly characteristics, as well as its cost-effectiveness and improved cooling efficiency compared to conventional flood cooling. This study investigates the end milling of AISI H11 die steel, utilizing a cooling system that involves a mixture of graphene nanoparticles (Gnps) and sesame oil for MQL. The experimental framework is based on a Taguchi L36 orthogonal array, with key parameters including feed rate, cutting speed, cooling condition, and air pressure. The resulting outcomes for cutting zone temperature and surface roughness were analyzed using the Taguchi Signal-to-Noise ratio and Analysis of Variance (ANOVA). Additionally, an Adaptive Neuro-Fuzzy Inference System (ANFIS) prediction model was developed to assess the impact of process parameters on cutting temperature and surface quality. The optimal cutting parameters were found to be a cutting speed of 40 m/min, a feed rate of 0.01 mm/rev, a jet pressure of 4 bar, and a nano-based MQL cooling environment. The adoption of these optimal parameters resulted in a substantial 62.5% reduction in cutting temperature and a 68.6% decrease in surface roughness. Furthermore, the ANFIS models demonstrated high accuracy, with 97.4% accuracy in predicting cutting temperature and 92.6% accuracy in predicting surface roughness, highlighting their effectiveness in providing precise forecasts for the machining process.