Research → Programmes → P04
P04 active

Local AI & Efficient Intelligence

Making AI more efficient, accessible and independent of centralised infrastructure, through local inference, model optimisation and resource-aware computing.

Research Areas

  • · Local model inference
  • · Quantisation and optimisation
  • · SLMs and specialised models
  • · Model routing
  • · Edge AI and resource-aware computing

Research Questions

  1. 01 What performance is achievable from quantised models on consumer hardware?
  2. 02 How should local AI systems route between models based on task requirements?
  3. 03 Can edge-deployed models match cloud performance on specialised tasks?

Research Projects

YR-003
Efficient Local Intelligence
Exploring Small Models, Local Inference and Context Efficiency
proposed

Publications

Publications from this programme will appear here as research projects progress through the YARA review and publication lifecycle.