A semiconductor inference device that has a non-volatile memory (NVM) array including NVM cells arranged in rows and columns, in which each NVM cell comprises a charge trapping transistor configured to store one of N×analog values corresponding to N×levels of its drain current (ID) or threshold voltage (VT) levels, representing N×weight values for multiply accumulate (MAC) operations. The semiconductor inference device also includes digital-to-analog (DAC) function and multiplexor (mux) function configured to generate an analog MAC result based on the digital inputs converted results and the weight values read results, and analog-to-digital (ADC) function configured to convert the analog MAC result of the mux function to a digital value. Other embodiments of the semiconductor inference device and related methods and systems are also disclosed.