<p>The machining industry is facing pressure to minimize environmental impacts and energy consumption in line with sustainability goals. In particular, conventional machining of difficult-to-machine alloys such as Ti-6Al-4V poses significant challenges in terms of environmental sustainability due to high-energy use, material waste, and carbon emissions. This study evaluates the machining performance of Ti6Al4V alloy during face milling by considering not only conventional machining outputs but also environmental indicators such as energy efficiency and carbon emissions. A full factorial experimental design was employed, incorporating three levels for each parameter: cutting speed (45–105 m/min), feed (0.04–0.14 mm/rev), and axial depth of cut (0.7–1.7 mm). The machining trials were conducted on a CNC vertical machining center using TiAlN-coated carbide inserts. Key machining outputs—cutting force, surface roughness, temperature, and tool wear—were systematically measured, with SEM utilized for detailed wear analysis. Based on the experimental data, an artificial neural network model with a 3–25-4 structure was developed. This model achieved high prediction accuracy for material removal rate, specific energy consumption, and carbon emissions, yielding a correlation coefficient greater than 0.98 and a prediction error of 2.47%. The optimal machining conditions were determined as a cutting speed of 75–90 m/min, feed of 0.040–0.065 mm/rev, and depth of cut between 0.70 and 0.95 mm. In addition, tool wear analyses indicate that at higher speeds, the build-up-edge formation is reduced. This study provides data-based contributions to sustainable manufacturing strategies by balancing energy efficiency and environmental impact.</p>