AI that runs in your browser
Ask anything about Yuta Hidaka. A small AI model running inside your browser answers. The model loads once and is then cached in your browser — no re-download afterward. You can also pick a no-download “No LLM” mode for instant answers.
Loading the model into your browser…
Mind your data usage (Wi-Fi recommended). It downloads once and is cached, so it is fast next time.
No server, no API key. Everything runs inside your browser.
Model (selectable)
Qwen2.5 0.5B / TinySwallow 1.5B
Choose the light Qwen2.5-0.5B (~0.5 GB, the default) or Sakana AI's Japanese-strong TinySwallow-1.5B (~1.2 GB, TAID-distilled). The model loads once, then is cached; a no-download “No LLM” mode is also available.
Runtime
transformers.js · WebGPU
Hugging Face · ONNX
The weights are 4-bit quantized ONNX — that is how a multi-GB model fits in ~0.5–1.2 GB, and why further compression does not help. They stream from Hugging Face once, then stay cached in your browser (no re-download). Inference runs on WebGPU (WASM fallback) inside a Web Worker, so the UI never freezes.
Grounding
Retrieval + fact-check
RAG + verify
Only the résumé facts relevant to your question are retrieved as context. After generation, names, numbers, and credentials are verified; anything unconfirmed is dropped and replaced with the real data.
Static site (Astro) · nothing sent to a server · no API key