Artifacts

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.

Click points on an image and get object masks from Segment Anything running in the browser.

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

Runs Microsoft's Florence-2 vision model in the browser for captioning, detection and OCR tasks.

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

Translates text between many languages with an NLLB model executed inside the browser through Transformers.js.

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

Open-weight text-to-speech that downloads the model once and runs in your browser.

Multilingual text-to-speech with voice cloning that runs entirely in the browser on CPU.

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.

Draw a few strokes and a Sketch-RNN model keeps drawing the object, with a model picker for subjects like birds.

Separates people from the background in webcam or video frames using TensorFlow.js segmentation models.

Detects a face mesh from webcam or video input using TensorFlow.js models in the page.

Finds hand keypoints in a webcam stream or video using TensorFlow.js models in the browser.

Tracks body keypoints from a webcam or video using MoveNet running through TensorFlow.js.

Type or pick sentences and see which are flagged as profane, sexually explicit or otherwise offensive by a TensorFlow.js model.

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.

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.