Any-to-Any
Transformers
Safetensors
English
gemma4
image-text-to-text
text-generation-inference
vllm
compressed-tensors
Instructions to use prithivMLmods/gemma-4-E4B-it-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prithivMLmods/gemma-4-E4B-it-NVFP4 with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("prithivMLmods/gemma-4-E4B-it-NVFP4") model = AutoModelForMultimodalLM.from_pretrained("prithivMLmods/gemma-4-E4B-it-NVFP4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- e96a17bb638d7e5c417d4c2abf3cdb5af7a97b50605a250f2f6d84c29b46d1d9
- Size of remote file:
- 32.2 MB
- SHA256:
- a2619fe11b50dbed06ac443c51d757b354d0b62d64baa514404d4e84e6713519
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.