Small model, with and without a Python tool

This page replays recorded runs. It is not live. Hugging Face now needs a PRO subscription to host a Gradio Space on the free CPU tier, so this Space is static. The runs below were recorded with this Space's own live/app.py on a 2-thread Linux machine (sandbox backend: bwrap), with a 1,024-token cap per answer. That cap is a demo setting. It is not the 25,000-token budget used in the evaluation, and a small cap exaggerates the gap because the no-tools side often runs out before it answers. To run it live, use live/app.py in this repo (cd live && pip install -r requirements.txt && python app.py) or the proxy in the tool repo. On a Mac the tool uses sandbox-exec (network denied by the OS, writes only in a temp dir). On Linux it uses bubblewrap when user namespaces work, and a weaker fallback otherwise.