Detecting insomnia from clinical narratives requires both accurate classification and clinically grounded reasoning with interpretable evidence. We present our systems for the SMM4H-HeaRD 2026 shared task, which leverages MIMIC-III notes annotated with rule-based insomnia criteria and supporting evidence spans. We explore two complementary approaches: parameter-efficient fine-tuning of lightweight models using QLoRA and LoRA, and few-shot prompting of large language models for joint reasoning and evidence extraction. Our best system achieves an F1-score of 0.7333 on binary classification and a micro-F1 of 0.6535 on multi-label rule prediction, with up to 0.5192 partial-match F1 for evidence extraction. Results show that lightweight fine-tuned models can outperform larger models in classification, while larger models demonstrate stronger reasoning but struggle with precise span localization, highlighting a key gap in clinically interpretable NLP systems.