Any-to-Any
Transformers
Safetensors
gemma4_unified
image-text-to-text
nvfp4
w4a16
vllm
compressed-tensors
gemma4
omni
dgx-spark
gb10
quantization
8-bit precision
Instructions to use coolthor/gemma-4-12B-it-NVFP4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use coolthor/gemma-4-12B-it-NVFP4A16 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("coolthor/gemma-4-12B-it-NVFP4A16") model = AutoModelForMultimodalLM.from_pretrained("coolthor/gemma-4-12B-it-NVFP4A16", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Ctrl+K