The usual approach for desinging a fast multiplier involves finding a way to quickly add up all the partial products, based on parital product recoding scheme and carry-save addition. This paper describes theoretical medels for area and time complexities of Multibit Reconding Paralle Multiplier (MRPM), which is a generalization of the modified Booth recoding scheme. Based on the proposed models, time performance, hardware requirements and area-time efficiency are analyzed in order to determine optimal recoding size for very large scale integration (VLSI) realization of the MRPM. Some simulation results show that the MRPM with large multiplier and multiplicand size has optimal area-time efficiency at the recoding size of 4-bit.