Artifacts

Hosted chat with Qwen3 models, with an optional thinking mode.

Chat with Gemma 3 12B, with image input and an adjustable system prompt.

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

Chat with a compact vision-language model about images you upload.

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

Chat demo of the efficient Gemma 3n E4B instruction model.

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

Runs several vision-language captioning models, such as DeepCaption and SkyCaptioner, on your media.

Chat with the small Llama 3.2 3B Instruct model.

Chat with Qwen3-VL about images or video clips.

Talk to Qwen2.5-Omni with text, images, audio or video and get text or speech back.

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.

Official Qwen3-Omni demo for chatting over text, images, audio and video.

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.

German-language fact checker: paste a claim or news excerpt and an AI model assesses its truthfulness using your Anthropic key.

Small vision-language model for describing images and video clips.

Answers your questions about computer science papers on arXiv using a language model.

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