About

About

Explore how on-device foundation models power edge GenAI with low latency, enhanced privacy and reliable offline performance. Learn about compression, acceleration and local Retrieval‑Augmented Generation (RAG) patterns for real-world deployments.

After completing this Pathway, you will be able to:

  • Use quantization and pruning to fit foundation models on edge devices
  • Examine and evaluate on-device inference pipelines for latency, privacy and reliability