This paper presents an extension of the Predictive Runtime Verification (PRV) paradigm to consider multiple models of the System Under Analysis (SUA). We call this extension Multi-Model PRV. Typically, PRV attempts to predict the satisfaction or violation of a property based on a trace and a (single) formal model of the SUA. However, contemporary node- or component-based systems (e.g. robotic systems) may benefit from monitoring based on a model of each component. We show how a Multi-Model PRV approach can be applied in either a centralised or a compositional way (where the property is compositional), as best suits the SUA. Crucially, our approach is formalism-agnostic. We demonstrate our approach using an illustrative example of a Mars Curiosity rover simulation and evaluate our contribution via a prototype implementation.