Over the years, the use of traditional metalworking fluids has negatively impacted worker health and the environment. Therefore, minimum quantity lubricant (MQL) has successfully proven to be effective in overcoming this problem. In addition, nanofluid-assisted MQL (NF-MQL) is one of the suggested techniques to further improve MQL performance, especially in the machining of hard-to-cut materials such as stainless steel. Therefore, in the present work, an attempt was made to improve the machining characteristics performance in turning of AISI 316L stainless steel under dry, MQL, and multi-walled carbon nanotubes (MWCNT)-assisted MQL conditions, with respect to surface roughness (Ra), feed force (Fz), and cutting temperature (CT). In this investigation, NF-MQL and pure MQL showed better results compared to dry condition; the results revealed that the Ra, CT, and Fz were found to be lower with 25.57%, 28.71%, and 22.84%, respectively, using pure MQL, and 39.16%, 42.38%, and 28.53% with NF-MQL. In the end, statistical analysis, regression modeling, and non-dominated sorting genetic algorithm (NSGA-II) is used to solve different multi-objective optimization problems, and technique for order of preference by similarity to ideal solution (TOPSIS) were performed.