This chapter fuses the flexibility of nonlinear and generalized models with random effect structures, yielding NLMMs and GLMMs. We articulate their marginal and conditional interpretations, describe approximation strategies, and address identifiability in high-level random coefficients. The chapter systematically compares NLMMs and GLMMs, illustrating when each is preferred, and provides a full estimation workflow—model building, convergence assessment, and inferential reporting.