🚧 📱

Mobile experience coming soon

Mobile development is in progress. Until it is complete, please use your desktop or laptop.

Thanks!

← Back
AI Engineer May 20, 2026

From 46% to 90%: Fine-Tuning Tiny LLMs for On-Device Agents — Cormac Brick, Google

Summary

The transcript discusses AI Edge technologies, focusing on small language models (SLMs and TLMs) and on-device AI capabilities for improved privacy, latency, and offline use. Key technologies mentioned include MediaPipe, Lighter TLM, and TensorFlow Lite runtime, which support running AI models across various platforms like Android, iOS, and others. The practical takeaway is that developers can now integrate small, customizable AI models directly into apps, running on different hardware like CPU, GPU, or NPU, with support for over 2.7 billion devices.

View original episode ↗