# Edge Inference: ONNX + Jetson + MediaTek NPU + Qualcomm AI Engine

> Source: https://sukruyusufkaya.com/learn/fine-tuning-cookbook/ftc-edge-inference-onnx-jetson-npu
> Updated: 2026-08-24T00:08:48.157Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part XV — Serving Engineering
**TLDR:** Edge LLM inference 2026'da gerçek: NVIDIA Jetson Orin, MediaTek NPU (Pixel), Qualcomm AI Engine (Snapdragon 8 Gen 3+), Apple Neural Engine. ONNX format için cross-platform inference, edge-spesifik quantization (INT8 / INT4 / W4A8 mixed), latency budget < 200 ms first-token. SmolLM3 1.7B + Pixel 8 Pro deploy reçetesi.