---
title: Everything WebGPU
emoji: ⚡
colorFrom: red
colorTo: yellow
sdk: static
pinned: false
---

# everything-webgpu — Interactive WebGPU LLM Playground

Run local MLC/WebLLM models directly on WebGPU in your browser with a priority scheduler, multi-step decoding, and zero-network disk loading.

- **GitHub**: [nyaaorick/everything-webgpu](https://github.com/nyaaorick/everything-webgpu)
- **Hugging Face Model**: [nyaaorick/everything-webgpu](https://huggingface.co/nyaaorick/everything-webgpu)
- **Qwen3.8 MLC Weights**: [nyaaorick/Qwen3.8-2B-q4f16_1-MLC](https://huggingface.co/nyaaorick/Qwen3.8-2B-q4f16_1-MLC)
- **npm Package**: [everything-webgpu](https://www.npmjs.com/package/everything-webgpu)