The numerical modelling of combustion phenomena is an important task due to safety issues and development and optimization of engines. Laminar burning velocity (LBV) is one of the most important physical properties of a flammable mixture. Knowing its exact value if crucial for assessment of flame stabilization, turbulent flame structure. It influences strongly safety, probability of knocking combustion and it is one of parameters used for assessment and development of detailed chemical kinetic mechanisms. Hence, the goal of this work is to develop models by means of Machine Learning algorithms for predicting laminar burning velocities of single-fuel C1-C7 normal hydrocarbon and air mixtures. Development of the models is based on a large experimental data set collected from literature. In total more than 1000, LBVs were accumulated for hydrocarbons from methane up to n-heptane. The models are developed in MATLAB 2018a with use of Machine Learning toolbox. Algorithms taken into account are multivariate regression, support vector machine, and artificial neural network. Performance of the models is compared with most widely used detailed chemical kinetics mechanisms’ predictions obtained with use of LOFEsoft. These kind of models might be efficiently used in CFD combustion models based on flamelet approach. The main advantage in comparison to chemical kinetics calculation is much shorter computational time needed for computations of a single value and comparable performance in terms of R2 (coefficient of determination), RMSE (root-mean-square error) and MAE (mean absolute error).