Messages go to a local worker running Qwen3.5 2B. The conversation stays in memory on your device, and the UI updates as tokens are generated.
- Uses a 4-bit model with WebGPU in a dedicated worker
- Downloads about 1.6 GB on first use, cached and shared with Number Extractor
- Streaming updates keep the UI responsive
- Supports text conversations; answers can be wrong, especially arithmetic
Model: Qwen3.5 2B ONNX, based on Qwen3.5 2B under the Apache 2.0 license.
Local LLM
Idle
Privacy-First & Local
How can I help you today?
I'm a private, local AI assistant running entirely in your browser.
Your first message downloads about 1.6 GB. The model is cached for future visits and shared with Number Extractor.
AI can make mistakes (specially this one running in a browser with limited resources). Consider checking important information.