AbstractOngoing rapid climate change is predicted to cause local extinction of plant species in mountain regions. However, some plant species could have persisted during Quaternary climate oscillations without shifting their range, despite the limited evidence from fossils. Here, we tested two candidate mechanisms of persistence by comparing the macrorefugia and microrefugia (MR) hypotheses. We used the rare and endemicSaxifraga florulentaas a model taxon and combined ensembles of species distribution models (SDMs) with a high‐resolution paleoclimatic and topographic dataset to reconstruct its potential current and past distribution since the last glacial maximum. To test the macrorefugia hypothesis, we verified whether the species could have persisted in or shifted to geographic areas defined by its realized niche. We then identified potentialMRbased on climatic and topographic properties of the landscape and applied refined scenarios ofMRdynamics and functions over time. Last, we quantified the number of known occurrences that could be explained by either the macrorefugia orMRmodel. A consensus of two or threeSDMtechniques predicted absence between 14–10, 3–4 and 1 kabp, which did not support the macrorefugia model. In contrast, we showed thatS. florulentacould have contracted intoMRduring periods of absence predicted by theSDMs and later re‐colonized suitable areas according to the macrorefugia model. Assuming a limited and realistic seed dispersal distance for our species, we explained a large number of the current occurrences (61–96%). Additionally, we showed thatMRcould have facilitated range expansions or shifts ofS. florulenta. Finally, we found that the most recent and the most stableMRwere the ones closest to current occurrences. Hence, we propose a novel paradigm to explain plant persistence by highlighting the importance of supporting functions ofMRwhen forecasting the fate of plant species under climate change.