Chandrasekhar-mass white dwarfs accreting mass from non-degenerate stellar companions through the single-degenerate channel have reigned for decades as the leading explanation of Type Ia supernovae. Yet, a comprehensive theoretical explanation has not yet emerged to explain the expected properties of the canonical near-Chandrasekhar-mass white dwarf model. A simmering phase within the convective core of the white dwarf leads to the ignition of one or more flame bubbles scattered across the core. Consequently, near-Chandrasekhar-mass single-degenerate SNe Ia are inherently stochastic, and are expected to lead to a range of outcomes, from subluminous SN 2002cx-like events, to overluminous SN 1991T-like events. However, all prior simulations of the single-degenerate channel carried through the detonation phase have set the ignition points as free parameters. In this work, for the first time, we place a single ignition point as predicted by {\it ab initio} models of the convective phase leading up to ignition, and follow through the detonation phase in fully three-dimensional simulations. Single-degenerates in this framework are characteristically overluminous. Using a statistical approach, we determine the $^{56}$Ni mass distribution arising from stochastic ignition. While there is a total spread of $\gtrsim$ 0.2 $M_{\odot}$. for detonating models, the distribution is strongly left-skewed, and with a narrow standard deviation of $\simeq 0.03 M_{\odot}$. Conversely, if single-degenerates are not overluminous but primarily yield normal or failed events, then our models require fine-tuning of the ignition parameters, or otherwise require revised physics or WD models. We discuss implications of our findings for the modeling of single-degenerate SNe Ia.