The concentrations of SiO2, Al2O3, K2O, Na2O, CaO, MgO, Fe2O3, TiO2 and loss on ignition (L.O.I.) stand for the main inorganic composition in geological samples. The concentrations of the 8 oxides and L.O.I. are also the main indicators of concern in the production of building ceramics. The quantitative analysis of these 9 contents were performed by the fiber laser based laser-induced breakdown spectroscopy (LIBS). The combination of the continuous background deduction, FWHM intensity integral and the spectral sum normalization was proposed for data processing. After the data processing combined the continuous background deduction, FWHM intensity integral and spectral sum normalization, the mean absolute errors (MAE) of the calibration of L.O.I., SiO2, Al2O3, K2O, Na2O, CaO, MgO, Fe2O3 and TiO2 reduce from 2.03%, 12.06% , 4.84%, 1.10%, 0.69%, 0.31%, 0.11%, 0.20%, 0.10% to 1.80%, 9.48%, 2.12%, 0.36%, 0.58%, 0.11%, 0.08%, 0.19% and 0.05%, respectively. The multivariate method was further introduced and discussed to improve the analysis performance. The MAEs of L.O.I., SiO2, Al2O3, K2O and Na2O were further reduced to 1.12%, 2.07%, 1.38%, 0.35% and 0.43%, respectively. The results show that the overall prediction error could meet the requirements in the production of building ceramics. The LIBS desktop analyzer has great potential in detection applications on geological samples.