In investing, every investor wants an optimal portfolio that generates a high return with minimal risk. There are many portfolio optimization models, among which is the Mean-Variance (MV) model. This model minimizes the portfolio variances that represents the risk in investment. The Artificial Bee Colony (ABC) is a heuristic method that can be used to solve the portfolio optimization problems. This method is inspired by the movement of honey bee colonies when searching for food. In this study, both the Cardinality-constrained mean-variance (CCMV) model and Improved Quick Artificial Bee Colony (iqABC) method were used. In this case, the CCMV model is a modification of the MV model which adds the cardinality constraint, quantity constraints, and the investor risk tolerance parameter. Meanwhile, the iqABC method is developed from the ABC method. The implementation shows that the choice of parameters in CCMV model must be chosen carefully, since the choice may help the investors compose the portfolio that suits their risk tolerance with diversification in mind. The implementation also shows the iqABC method on CCMV model generates a portfolio with better returns and Sharpe ratio values compared to those of mABC methods and the market.