Curriculum Hub

Domain Hub · 2 Interactive Modules

Edge AI & Efficient Models

Compress and run foundation models on low-power edge hardware with knowledge distillation, post-training quantization (PTQ/QAT), and INT4/INT8 integer arithmetic.

Domain Modules & Concepts

Concept 3 Topics

Small Language Models (SLM)

SLMs deliver near-LLM capability with a fraction of the parameters, enabling local execution on edge devices. Knowledge distillation and domain specialisation are the key techniques.

Domain Distillation Parameter Efficiency Local Execution
Explore Concept →
Concept 4 Topics

Model Quantisation

Quantisation reduces model weight precision from 32-bit floats to 8-bit or 4-bit integers, cutting memory footprint 4–8× and accelerating inference on integer-optimised hardware.

PTQ QAT INT4/INT8 Compression Hardware Optimization
Explore Concept →