Structured Pruning of Small Language Models: An Empirical Study on GQA-Aware Attention and MLP Compression with LoRA Recovery (A. BAKKOU, B. Hirchoua, M. Banane, & N. . Er-raji, Trans.). (2026). International Journal of Advances in Soft Computing and Its Applications , 18(3), 113–139. https://doi.org/10.15849/ijasca.171