Meteorological observations at high elevations in mountainous regions are often lacking. One opportunity to fill this data gap is through the use of downscaled output from weather reanalysis models. In this study, we tested the accuracy of downscaled output from the North American Regional Reanalysis (NARR) against high-elevation surface observations at four ridgetop locations in the southern Coast Mountains of British Columbia, Canada. NARR model output was downscaled to the surface observation locations through three-dimensional interpolation for air temperature, vapour pressure and wind speed and two-dimensional interpolation for radiation variables. Accuracy was tested at both the 3-hourly and daily time scales. Air temperature displayed a high level of agreement, especially at the daily scale, with root mean square error (RMSE) values ranging from 0.98 to 1.21 °C across all sites. Vapour pressure downscaling accuracy was also quite high (RMSE of 0.06 to 0.11 hPa) but displayed some site specific bias. Although NARR overestimated wind speed, there were moderate to strong linear relations (r2 from 0.38 to 0.84 for daily means), suggesting that the NARR output could be used as an index and bias-corrected. NARR output reproduced the seasonal cycle for incoming short-wave radiation, with Nash–Sutcliffe model efficiencies ranging from 0.78 to 0.87, but accuracy suffered on days with cloud cover, resulting in a positive bias and RMSE ranged from 42 to 46 Wm− 2. Although fewer data were available, incoming long-wave radiation from NARR had an RMSE of 19 Wm− 2 and outperformed common methods for estimating incoming long-wave radiation. NARR air temperature showed potential to assist in hydrologic analysis and modelling during an atmospheric river storm event, which are characterized by warm and wet air masses with atypical vertical temperature gradients. The incorporation of a synthetic NARR air temperature station to better represent the higher freezing levels resulted in increased predicted peak flows, which better match the observed run-off during the event.