Artifacts

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

Real-time object detection and pose estimation on a webcam or image using YOLO26 in the browser.

Whisper speech recognition running on the Ratchet WebGPU runtime inside the browser.

Generates embeddings with EmbeddingGemma 2 on WebGPU directly in the browser.

Real-time captions for webcam video generated by an LFM2-VL model inside the browser.

Whisper transcription compiled to WebAssembly with Rust Candle, running in the page.

Fetches a GitHub repository and merges its files into one text file for pasting into an LLM.

Detects and masks personal information in text, running locally in your browser.

Live webcam captioning and object tracking using a 450M vision-language model 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.

Writes a GitHub issue draft with SmolLM2 running locally in the browser on WebGPU.

Translates text between 56 languages with a 4B TranslateGemma model running privately in the browser.

Text-to-image model running fully in the browser on WebGPU, per the Space description.

Generate structured output such as JSON from an in-browser WebLLM model.

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

Translates text between languages with a model that runs in the browser.

Shows a live depth map of your webcam feed computed on the GPU in the browser.

Removes the background from webcam video frames in real time using a WebGPU model.

Embeds sentences with Qwen3 in the browser and plots them on a 2D scatterplot by meaning.

Search a photo set by describing it in words, with CLIP embeddings computed in the browser.

IBM Granite speech recognition running locally through WebGPU in the browser.

Demo that summarises web page text with a Liquid AI model run locally in the browser.