LiquidAI/LFM2-VL-450M-WebGPU

LFM2-VL-450M WebGPU Demo

In-browser vision-language inference with LFM2-VL-450M, powered by ONNX Runtime and WebGPU.

Everything runs entirely in your browser with WebGPU acceleration - no data is sent to a server.

Features

• —Live Webcam Captioning: Stream from your webcam with real-time AI-generated captions
• —Multiple Precision Options: Choose between FP16 (~1.05 GB) or FP32 (~2.1 GB)
• —Browser Caching: Models are cached locally after first download for faster subsequent loads
• —Adjustable Resolution: Configure capture resolution (256-512px) for performance tuning

Requirements

• —WebGPU-enabled browser
• —~1-2 GB memory depending on precision choice
• —Webcam access for live captioning