---
license: gemma
tags:
- litert-lm
- android
- on-device
- function-calling
- brief-ai
library_name: litert-lm
pipeline_tag: text-generation
---

# Brief AI Lite

Brief AI Lite is the optional local model package for Brief's Ask Brief assistant.

This repository is intended for development and beta distribution of the app-private on-device model file. Brief downloads the model only after explicit user action, stores it in app-private storage, verifies the file before use, and falls back to deterministic local tools when the model is missing or invalid.

## Files

- `mobile-actions_q8_ekv1024.litertlm`
- `model_manifest.json`

## Manifest

```json
{
  "model": "Brief AI",
  "version": "0.1.0",
  "file": "mobile-actions_q8_ekv1024.litertlm",
  "sizeBytes": 285561008,
  "sha256": "9a9c590143b6a88ecaf074c574c2bfe311ba4160559b9e105fa4ac4ef0b57aef",
  "runtime": "LiteRT-LM",
  "format": "litertlm",
  "use": "Ask Brief routing and safe local actions",
  "storage": "App-private after explicit user download",
  "privacy": "No notification content should be uploaded to use this model."
}
```

## Privacy Boundary

Brief should not upload notification content to use this model. The app should provide only sanitized local metadata and allowlisted tool schemas to the model, and deterministic Brief logic must validate tool calls, references, counts, privacy rules, and rule drafts.

## License

This model is derived from Google's Gemma / FunctionGemma family and is distributed under the Gemma license terms.