Instructions to use nalsil/notivault-gemma3-mirror with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use nalsil/notivault-gemma3-mirror with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Gemma 3 1B-IT (LiteRT .task) β NotiVault distribution mirror
This repository is an unmodified redistribution mirror of the LiteRT (.task) builds of
Gemma 3 1B-IT, originally published at
litert-community/Gemma3-1B-IT.
It exists so that the NotiVault
Android app can download the on-device model directly, without requiring each end user to hold a
Hugging Face account and access token.
| File | Quantization | Size |
|---|---|---|
gemma3-1b-it-int4.task |
int4 | ~555 MB |
Gemma3-1B-IT_multi-prefill-seq_q8_ekv1280.task |
q8 (ekv1280) | ~1.05 GB |
The files are byte-identical to the originals (SHA-256 checksums are pinned and verified by the app on every download).
License and Terms β Gemma
Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms.
By downloading or using these files you agree to the Gemma Terms of Use, including the Gemma Prohibited Use Policy at ai.google.dev/gemma/prohibited_use_policy.
Notice required by the Gemma Terms of Use:
Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms.
This mirror adds no modifications, fine-tuning, or derivative changes. All rights in the model remain with Google. If you are the rights holder and want this mirror amended or removed, please open a discussion in this repository.
- Downloads last month
- -