Artifacts

Loads a GGUF model with a WebAssembly llama.cpp build and generates text in the browser.

Chat with open language models that download into your browser and run on WebGPU without a server.

Chat, write, translate and transcribe with AI models downloaded to and run on your device.

Runs a Gemma 4 model in the browser with custom WebGPU kernels, so chat needs no server.

Points your webcam at a scene and has a small vision-language model describe it continuously, locally on WebGPU.

Chat playground that downloads open models and runs them locally on WebGPU with WebLLM.

Runs Phi-1 and Phi-2 text generation in WebAssembly through Rust Candle with no server.

Runs the llama2.c small Llama model in WebAssembly with Rust Candle, generating text in the page.

Multimodal chat with Qwen 3.5 vision models running locally via Transformers.js and WebGPU.

Demonstrates a small model calling tools from the browser using Transformers.js and WebGPU.

A compact reasoning-capable Nemotron model that runs in the browser on WebGPU.

An on-device research agent built on LFM2.5 2.6B that runs through WebGPU in the browser.

Ask questions about a picture using the Moondream vision-language model running locally on WebGPU.

Loads the open-weight GPT-OSS 20B model into WebGPU memory so you can chat without a server.

Runs the very small LFM2.5 230M language model with custom WebGPU kernels in the tab.

Small vision-language model that captions and answers questions about images locally on WebGPU.

Official WebLLM demo that loads a model into the browser and answers prompts without a backend.

Phi language model executed in the browser using the Ratchet WebGPU runtime.

Chatbot using the Phi-3.5 model downloaded into your browser and executed with WebGPU.

Minimal chat page where a Qwen2 model runs on your GPU in the browser using Transformers.js.

Multimodal 2B model that runs locally in the browser on WebGPU.

Runs an agent loop in the browser tab on top of a ternary Bonsai 2 model using WebGPU.

A small coding agent powered by a 1.7B LFM3 model that runs locally via WebGPU.

Describe and question images with the small nanoLLaVA model running in your browser.