Instructions to use webgpu/Qwen3-4B-ONNX_Init with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use webgpu/Qwen3-4B-ONNX_Init with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'webgpu/Qwen3-4B-ONNX_Init');