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
Thank you Google team
#16
by jreoka - opened
I can tell you for a fact the community truly appreciates these models. Feel free to keep them coming! ๐ฅ๐ฅ๐ฅ
i love Gemma
i love GOOGLE
โค๏ธ
Honestly it's not bad but I keep going back to Qwen3.6 my biggest issue I have had with Gemma is I had been making a music player I gave it direct instructions not to touch my player bar and it changed my icons it terrible emojis and honestly destroyed my whole player luckily I had it's original code as a restore point.
So I may end up using Gemma in game development or something instead.