FAQ
Local AI
What the local model is, and what it runs on.
Is this Gemini?
No. The one runnable model is a community Gemma conversion, and its output is not a Gemini result.
Source: docs/generation.md (3 model identity), README.md (what runs)
Link to this answer Does it use a GPU?
No. CPU only.
Source: docs/compatibility.md (vertex ai custom prediction)
Link to this answer
Build against Google Cloud APIs, locally
Free and open source under Apache-2.0. No account, no sign-up, no Google Cloud bill.