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:
# 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
Vuk
#7
by d3rlord3 - opened
Jj
Yo
Hi @d3rlord3 -
If you have a question, feedback, or a specific topic you'd like to discuss regarding google/gemma-4-12B model, please share more details. We'd be happy to help!
Hello there!
I'm really impressed by the fact that this model supports so many different types of inputs. I was wondering if there are any free online platforms where I can test it. I would greatly appreciate any suggestions. Thanks!
Hi @SamanKd -
Thank you for your interest! You can try coding or running Gemma models using Hugging Face or Ollama. For GUI-based setup, you can use LM Studio.