Free AI assistants and chat tools

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.

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.

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.

Ask questions about images and videos with the 32B Qwen2.5-VL model.

Generates a short caption describing an uploaded picture, running on CPU.

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

Scores an AI prompt, gives feedback and suggests a better version.