license: gemma
tags:
- on-device
- android
- litert-lm
- gemma
base_model:
- google/gemma-3-1b-it
- google/gemma-3n-E2B-it
EdgeAgent models
Mirror of three Gemma models in .litertlm format, used by the EdgeAgent Android app, where every
AI feature runs on the phone. Nothing here is modified — these are the published weights, re-hosted
so the app has a stable download URL.
Licence
Gemma is provided under and subject to the Gemma Terms of Use: https://ai.google.dev/gemma/terms
Prohibited uses: https://ai.google.dev/gemma/prohibited_use_policy
By downloading these files you agree to the Gemma Terms of Use. If you redistribute them, or a model derived from them, you must pass this notice on and include the same use restrictions.
Files
| File | Size | Upstream | SHA-256 |
|---|---|---|---|
gemma3-1b-it-int4.litertlm |
584 MB | litert-community/Gemma3-1B-IT |
1325ae366d31950f137c9c357b9fa89448b176d76998180c08ceaca78bba98be |
functiongemma-mobile-actions.litertlm |
284 MB | litert-community/functiongemma-mobile-actions_q8_ekv1024.litertlm |
92109695f911d1872fa8ae07c1e3ff0ed70f2c3d1690d410ec6db8587c2ab409 |
gemma3n-e2b-it-int4.litertlm |
3.6 GB | google/gemma-3n-E2B-it-litert-lm |
2ed7bc3a0026c93d5b8a4544b352d9d00cd66ff0bac3ef6a20ac3d2cba4010d6 |
The app checks every download against these digests and refuses anything that does not match, so a corrupted or substituted file fails loudly instead of loading quietly.
Use
These files are for the LiteRT-LM runtime on Android. They are not PyTorch checkpoints and will
not load with transformers.