Bringing Gemma 4 12B to your Laptop: Unlocking Local, Agentic Workflows with Google AI Edge- Google Developers Blog
Jun 3, 2026Google AI Edge Team

Summary
This post details the integration of Gemma 4 12B with the Google AI Edge stack for local, agentic workflows. It introduces the 'serve' command in the LiteRT-LM CLI for local LLM serving, compatible with standard tools and SDKs. It also highlights the capabilities of Google AI Edge Gallery for on-device coding tasks (data analysis, script generation, 3D rendering) and Google AI Edge Eloquent for on-device dictation and voice-driven editing, emphasizing the performance and quality improvements of Gemma 4 12B in these applications.
More from the Coral Edge AI Platform trail
- ML Drift: Next-Gen GPU AI/ML Inference at the Edge- Google Developers Blog
- Bring multimodal semantic search to the edge with EmbeddingGemma 2- Google Developers Blog
- EmbeddingGemma 2: The Developer Guide- Google Developers Blog
- Mastering Edge AI on Raspberry Pi with LiteRT and Gemma- Google Developers Blog
- LiteRT.js, Google's high performance Web AI Inference- Google Developers Blog