Provide a short but precise answer.

A researcher wants to design a balanced experiment with r replications of two factors, F, at 5 fixed levels and F2 at 2 fixed levels. What is the smallest value of r which would yield an F test of the main effect of factor F, with o = .05 and power 0.80 to detect a difference of at least 6 units between any pair of factor F, means if the variance ge is approximately 6.5