Instructions to use google/gemma-4-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-4-12B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/gemma-4-12B") model = AutoModelForMultimodalLM.from_pretrained("google/gemma-4-12B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from google/gemma-4-12B: direct link, hf CLI and curl.
- Browser
- Download file 32.2 MB
-
https://huggingface.co/google/gemma-4-12B/resolve/refs%2Fpr%2F13/tokenizer.json
- Command line
-
hf download hf://google/gemma-4-12B@refs/pr/13/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/google/gemma-4-12B/resolve/refs%2Fpr%2F13/tokenizer.json
32.2 MB
- Xet hash:
- e95ce246e26231dc312210ed2b60cfe45ac83869ad5299ac973a634e8fc16e2f
- Size of remote file:
- 32.2 MB
- SHA256:
- 42cacba08980fc39bfe2c73cb8c4486b9d00f2f2671072c6cb9c45ee2c5cfaae
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.