Octanol/water (KOW) and octanol/air (KOA) partition coefficients are two important physicochemical properties of organic substances. In current practice, KOW and KOA values of some polychlorinated biphenyls (PCBs) are measured using generator column method. Quantitative structure–property relationship (QSPR) models can serve as a valuable alternative method of replacing or reducing experimental steps in the determination of KOW and KOA. In this paper, two different methods, i.e., multiple linear regression based on dragon descriptors and hologram quantitative structure–activity relationship, were used to predict generator-column-derived log KOW and log KOA values of PCBs. The predictive ability of the developed models was validated using a test set, and the performances of all generated models were compared with those of three previously reported models. All results indicated that the proposed models were robust and satisfactory and can thus be used as alternative models for the rapid assessment of the KOW and KOA of PCBs.