Small language models with Google AI Edge

Estimated read time 2 min read

Post Content

​ Discover a new app development paradigm where users interact naturally with apps, blurring the lines between human language and digital action. We’ll demo newly released libraries, which allow local agents to drive applications and devices by combining on-device LLMs with native audio input, retrieval augmented generation, and function calling. Learn how to accelerate on CPU, GPU, or NPU, and a tutorial on how to test ML workflows on real devices via the cloud using Google AI Edge Portal. The session will include real production features from our current 3P EAP partners.

Resources:
For more information → goo.gle/ai-edge
LiteRT acceleration updates → https://goo.gle/3FnDGOr
GPU Updates → https://goo.gle/3ScpzhS
NPU EAP Signup → https://goo.gle/44NuNbo
Sample App → https://goo.gle/4mqk9O9
AI Edge Portal → https://goo.gle/43F58k8
AI Edge Portal EAP Signup → https://goo.gle/436hYaT

Speakers: Matthias Grundmann, Mark Sherwood, Mogan Shieh

Check out the AI session track from Google I/O 2025 → https://goo.gle/io25-ai-yt
Check out all of the sessions from Google I/O 2025→ https://goo.gle/io25-sessions-yt

Subscribe to Google for Developers → https://goo.gle/developers

Event: Google I/O 2025

Products Mentioned: AI/Machine Learning   Read More Google for Developers 

You May Also Like

More From Author