Nanobodies (Nbs) achieve high solubility and stability due to the presence of four conserved residues refereed to as the Nb tetrad. While several stud-ies have highlighted the importance of the Nbs tetrad to their stability, a de-tailed molecular picture of their role has not been provided. In this work, we have used the Rosetta package to engineer synthetic Nbs lacking the Nb tetrad and used the Rosetta Energy Function to assess the structural features of the native and designed Nbs concerning the presence of the Nb tetrad. Our results show that these two classes of Nbs differ significantly in fea-tures related to solvation energy and native-like structural properties. No-tably, the loss of stability occasioned by the loss of the tetrad is chiefly driven by the entropic contribution. To develop a classificatory model, we have benchmarked three different machine learning (ML) and deep learning (DL) algorithms and concluded that the higher the complexity of the model, a better binary classification was achieved for our dataset.