Assess students’ ability to apply model-compression and quantization techniques to optimize deep neural networks for edge deployment. Scope: analyze hardware constraints (memory, latency, power), choose and implement methods (pruning, weight sharing, low‑rank factorization, post‑training quantization, quantization‑aware training, mixed precision), integrate into training/deployment pipelines, evaluate trade‑offs (accuracy, throughput, energy) using benchmarks and tooling (TFLite, ONNX, TensorRT), and justify technique selection for a specified edge scenario.