# NimbleEdge

- **Event:** [Edge Deployments & On-Device AI Hackathon](https://cerebralvalley.ai/e/executorch-hackathon)
- **When:** Mon, Oct 20 at 9:00 AM – 9:00 PM (PDT)
- **Where:** 275 Brannan Street, San Francisco, CA
- **Team:** [Varun Khare](https://cerebralvalley.ai/u/vkkhare)
- **GitHub:** https://github.com/meta-pytorch/executorch-examples/pull/101
- **Demo video:** https://drive.google.com/file/d/1am8dOyMueftBi1b1Kx6qvA1D8jOzeOyT/view?usp=sharing
- **Gallery:** https://cerebralvalley.ai/e/executorch-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/executorch-hackathon/hackathon/gallery/11

Does tool calling through Qwen 3 and QNN hardware acceleration loading the model over executorch. The model understands when asked about weather "here" goes to fetch location as a tool call.

---

Markdown version of https://cerebralvalley.ai/e/executorch-hackathon/hackathon/gallery/11. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt