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, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/gemma-4-12B-it") model = AutoModelForMultimodalLM.from_pretrained("google/gemma-4-12B-it", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Thanks again!
I have now tried the instruct version this version. And I can say again Google cooked again.. and I was literally asking for a 12-14B models 2 months ago.. and ya guys just answered my wish.. thanks google devs! Or engineers!
You guys are better than Qwen and other companies in making AI stuff ๐ that's my opinion tho.
Hi @JanjanJean -
Thanks for the feedback. Let us know if you face any bugs while setting it up, and definitely share if you build anything cool with it.
Actually quite good. especially in images. generally good in other languages too. realy understand speach well but not doing great with other sounds. couldnt identify animal sounds.
https://ady.com.tr/blog/#/gemma-4-12b
Hi @adyady , Are you trying to input an audio file and identify which animal sound it is? Could you share a bit more details so we can reproduce this on our end?