This paper presents predictive fuzzy modeling of nonlinear plant. Three different fuzzy models are presented, where the first one is synthesized using Mamdani type rule base, the second - Takagi-Sugeno type rule base. The experimental results show advantages and disadvantages of the presented models and their adequacy to the nonlinear plant. A hybrid modeling approach was offered to eliminate the disadvantages of the Mamdani and the Takagi-Sugeno fuzzy models. The advantages of the hybrid model are experimentally proved and presented in this paper.