This study investigates face milling of austenitic stainless steel under sustainable dry and Minimum Quantity Lubrication (MQL) conditions, with material removal volume (MRV) as the primary response variable. Austenitic stainless steel poses significant machining challenges due to its low thermal conductivity, high ductility, and work hardening tendencies, exacerbating tool wear mechanisms like notching and chipping. A full factorial design of experiments was conducted, varying cutting speed and feed per tooth, to evaluate their effects on MRV. Quadratic regression models were developed, incorporating Box-Cox transformations for improved robustness and predictive accuracy. Monte Carlo simulations were employed to assess robustness and process variability. Results show that dry machining yields a higher MRV (optimal: 250 cm³ at 213 m/min, 0.20 mm/tooth), while MQL provides a higher material removal rate but lower MRV (optimal: 231 cm³ at 170 m/min, 0.32 mm/tooth), illustrating the trade-off between tool life and short-term productivity. Experimental validation with new test conditions confirmed the accuracy and robustness of the regression models, with predictions closely matching observed results within a 95% prediction interval. Monte Carlo simulations further highlighted that dry machining resulted in higher MRV with greater variability, while MQL gave more consistent but lower MRV values. Observations of notch wear and cracks (most plausibly associated with thermal fatigue) under MQL motivated a preliminary tool modification that redirected the MQL jet away from the cutting edge during tool exit, showing up to 25–50% improvement in MRV. These findings contribute to sustainable machining strategies by providing actionable insights into parameter selection for improved efficiency and durability in industrial applications.