Running Gemma4-E2B tool calling locally on an iPhone

Melvin Vivas · X post · 2026-09-19 · Open on X

Topics: AI Agents, Tool Use & MCP, LLMOps, Deployment & Monitoring · Level: intermediate

Summary

The creator reports getting tool calling working with Gemma4-E2B running fully on-device on an iPhone. This shows that small open models can now support agent-style tool use on mobile hardware without a cloud API.

Key points

• Gemma4-E2B is small enough to run locally on an iPhone.
• It supports tool (function) calling on-device, so local mobile agents are possible.
• Running on-device avoids API costs and keeps data private.

Resources mentioned

• Google Gemma (@googlegemma) · person · x.com · free
  Official X account for Google's Gemma open models, with release news and examples.
  Also in: Running Gemma 4 Models Offline on an iPhone (Melvin Vivas on X · notes)
• Gemma 4 · tool · ai.google.dev · free
  Google's family of open-weight models in several sizes, built to run on devices and offline, with multimodal and agentic abilities, and open to fine-tuning.
  Also in: Gemma 4 Runs Locally On-Device in the Antigravity SDK (Melvin Vivas on X · notes), On-Device AI: Running Gemma 4 E2B Offline on an iPhone with LiteRT (Melvin Vivas on X · notes), Running Gemma 4 Models Offline on an iPhone (Melvin Vivas on X · notes), Fine-tuning Gemma4-E2B on your own tweet style with Unsloth (Melvin Vivas on X · notes) and 25 more

Try this

• Build an on-device iPhone assistant that uses Gemma4-E2B tool calling locally.