Instructions to use litert-community/gemma-3-270m-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use litert-community/gemma-3-270m-it with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install -U litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli litert-lm run \ --from-huggingface-repo=litert-community/gemma-3-270m-it \ --prompt="Write me a poem"
- Notebooks
- Google Colab
- Kaggle
Safetensors to tflite
#3
by salmankhanpm - opened
Hi, Is there any Documentation or code on how to convert a model to LiteRT. I am planning to do sft and inference on edge ( mobile ) via Edge Gallery.
Thank you
Hi
P.M.SALMAN KHAN, Did you find any solution so far. I too looking for the same for quite sometime but couldnt find anything yet
There's a guide to LiteRT fine-tuning available here: https://developers.googleblog.com/own-your-ai-fine-tune-gemma-3-270m-for-on-device/. For mobile or Edge Gallery, this is probably what you want.
Small caveat: this will not work for larger models on web yet; see my post in the other thread for guidance on "-web.task" Gemma3 models.