Abstract: US veterans are significantly more likely than civilians to die by suicide. Machine-learning models have been developed to target high-risk transitioning service members for suicide prevention interventions to reduce veteran suicides. These models are suicide method-agnostic. However, firearms are involved in most veteran suicides, and firearm-specific preventions exist. We used data from US Army veterans from 2010 to 2019 (N = 800,579) to develop and compare firearm-specific machine-learning models with a method-agnostic model to predict firearm suicides among transitioning Army veterans up to 10 years after discharge. The models performed comparably overall (area under the receiver operating characteristic curve = 0.710–0.708; integrated calibration index = 0.0003–0.0005% for firearm-specific and method-agnostic models, respectively), with the best model depending on the intervention threshold. Results from this study show the method-agnostic model was better at predicting firearm suicides at the highest intervention threshold, whereas the firearm-specific model was better at lower thresholds. When considering fairness with respect to sex and race/ethnicity, the firearm-specific model was best across all thresholds. Thus, model choice depends on weighing numerous factors, and optimal thresholds might differ for coordinated firearm-specific and method-agnostic interventions.