Instructions to use google/gemma-4-12B-it-qat-w4a16-ct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-4-12B-it-qat-w4a16-ct with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/gemma-4-12B-it-qat-w4a16-ct") model = AutoModelForMultimodalLM.from_pretrained("google/gemma-4-12B-it-qat-w4a16-ct", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Google, Open Source Old Bison PaLM 2 Model In 2026/27
#6
by Tralalabs - opened
Open-Source chat-bison@001. It's very old in 2026, it's deprecated. That means we can't use it anymore. Lost media. Upload model weights. In model card, add how many params + how many training tokens. Would like to see it in July-September 2026! PaLM 2 is old! Goooo! please, google! ya can do it!