In this paper the Adaptive Neuro-Fuzzy Inference System (ANFIS) is used for the prediction of thermal efficiency and thermal resistance of a two-phase closed thermosyphon (TPCT). Aqueous suspensions of pristine multiwalled carbon nanotubes (CNTs) and functionalized CNTs with ethylene diamine were used as nanofluid in the TPCT. The experimental results regarding the TPCT performance including thermal efficiency and thermal resistance were modeled by the ANFIS technique. The ANFIS network was initiated by 70% of experimental data, and 30% of primary data were considered for testing and checking the suitability of the ANFIS model. The modeling results were compared with five arithmetical criteria. The arithmetical criteria suggested that the obtained modeling by ANFIS is valid and it could be expanded for other conditions. Also, to determine optimal ranges of experimental conditions, three-dimensional diagrams were traced by the modeling data. The proposed method of ANFIS modeling may be applied for optimization of other TPCTs with different configurations.