Instructions to use google/gemma-4-12B-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-4-12B-it with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("google/gemma-4-12B-it") model = AutoModelForImageTextToText.from_pretrained("google/gemma-4-12B-it") - Notebooks
- Google Colab
- Kaggle
NVFP4 / FP8 Quantizations
#19
by vincentzed-hf - opened
Unofficial-- feel free to try these!!
https://huggingface.co/AxionML/Gemma-4-12B-NVFP4
https://huggingface.co/AxionML/Gemma-4-12B-FP8
Hi @vincentzed-hf ,
Thank you so much for taking the time to provide these quantized versions. We truly appreciate your efforts on the potential for NVFP4 and FP8 quantized versions of Gemma-4-12B model.