---
license: llama3.2
---

ONNX version of [Llama 3.2 Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B) model, quantized for inference on the [Snapdragon 8 Elite](https://www.qualcomm.com/products/mobile/snapdragon/smartphones/snapdragon-8-series-mobile-platforms/snapdragon-8-elite-mobile-platform) NPU.