In this paper, the finite-time fault detection problem for quantized large-scale networked systems is investigated. A nonlinear Markovian jump system model with partially unknown transition probabilities is employed to describe the Makov data assignment pattern. Based on this obtained model, in finite-time stability framework, the desired mode-dependent fault detection filter is constructed such that the augmented error system is finite-time stochastically stable with H∞ attenuation level. Especially, the sufficient conclusions provide quantitative relationship between network characteristic, quantization level and finite-time system parameter with finite-time fault detection performance. The effectiveness of the proposed method is demonstrated by simulation examples.