There is a method to test the required sample size of the models based on monte carlo simulation, you just need to imput the expected coefficients and several sample sizes to test if coverage is optimal.
Muthén, L. K., & Muthén, B. O. (2002). How to use a Monte Carlo study to decide on sample size and determine power. Structural Equation Modeling, 9(4), 599-620.
Generalmente el tamaño de la muestra depende de la complejidad del modelo. Modelos mas simples y con menos parametros a estimar, son muestras mas chicas. Modelos mas complejos, muestras mascgrandes. Esta relacionado con la potencias estadistica.