Instructions to use google/gemma-4-E4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-4-E4B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/gemma-4-E4B") model = AutoModelForMultimodalLM.from_pretrained("google/gemma-4-E4B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- AMD Developer Cloud
Download tokenizer.json from google/gemma-4-E4B: direct link, hf CLI and curl.
- Browser
- Download file 32.2 MB
-
https://huggingface.co/google/gemma-4-E4B/resolve/refs%2Fpr%2F7/tokenizer.json
- Command line
-
hf download hf://google/gemma-4-E4B@refs/pr/7/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/google/gemma-4-E4B/resolve/refs%2Fpr%2F7/tokenizer.json
32.2 MB
- Xet hash:
- cff735875d3f03a2bc4d79f346058167ba735369ac624a106ba2da165fad4c11
- Size of remote file:
- 32.2 MB
- SHA256:
- 7b512484de7440c449024ae8686cb8dbab12f2cf59bb53aaa89760cd6d86320a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.