This paper presents a new robust method for inertial MEM (MicroElectroMechanical systems) 3D gesture recognition. The linear ac- celeration and the angular velocity, respectively provided by the accele- rometer and the gyrometer, are sampled in time resulting in 6D values at each time step which are used as inputs for the gesture recognition system. We propose to build a system based on Bidirectional Long Short- Term Memory Recurrent Neural Networks (BLSTM-RNN) for gesture classification from raw MEM data. We also compare this system to a ge- ometric approach using DTW (Dynamic Time Warping) and a statistical method based on HMM (Hidden Markov Model) from filtered and de- noised MEM data. Experimental results on 22 individuals producing 14 gestures in the air show that the proposed approach outperforms classi- cal classification methods with a classification mean rate of 95.57% and a standard deviation of 0.50 for 616 test gestures. Furthermore, these experiments underline that combining accelerometer and gyrometer in- formation gives better results that using a single inertial description.