The oceanic neodymium isotopic composition (hereafter expressed as ε <sub>Nd</sub>) is modeled for the Last Glacial Maximum (LGM) using the coarse resolution Ocean Global Circulation Model NEMO–ORCA2°. This study focuses on the impact of changes in the overturning cell and circulation patterns between LGM and Holocene on ε <sub>Nd</sub> in the Atlantic basin. Three different LGM freshwater forcing experiments are performed to test the variability in ε <sub>Nd</sub> oceanic distribution as a function of ocean circulation. Highly distinct representations of ocean circulation are generated in the three simulations, which drive significant differences in ε <sub>Nd</sub>, particularly in deep waters of the western part of the basin. However, mean Atlantic LGM ε <sub>Nd</sub> values are remain half a unit more radiogenic than for the modern control run. A fourth experiment shows that changes in Nd sources and bathymetry drive a shift in the ε <sub>Nd</sub> signature of Northern end-members (NADW or GNAIW glacial equivalent) that is sufficient to explain the shift in mean ε <sub>Nd</sub> during our LGM simulations. None of our three LGM circulation scenarios gives a better agreement with the existing ε <sub>Nd</sub> paleo-data, as the model fails in reproducing the dynamical features of the area. Therefore, this study cannot indicate the likelihood of a given LGM oceanic circulation scenario. Rather, our modeling results highlight the need for data from western Atlantic deep waters, where the ε <sub>Nd</sub> gradient in the three LGM scenarios is the most important (up to 3 ε <sub>Nd</sub>). This would also aid more precise conclusions concerning the north end-member ε <sub>Nd</sub> signature evolution, and thus the potential use of ε <sub>Nd</sub> as a tracer of past oceanic circulation.