📄 About This Model
FP8-dynamic quantized variant of gemma-4-12B-it.
Model Details
Full Model IDRedHatAI/gemma-4-12B-it-FP8-Dynamic
Pipeline / Taskany-to-any
Librarytransformers
Downloads (all-time)15.2K
Likes9
Last Modified9/15/2026
Author / OrgRedHatAI
PrivateNo — public
⚡ Quick Usage (Python)
Using the 🤗 Transformers library. Install with pip install transformers
from transformers import pipeline
# Load the model
pipe = pipeline("any-to-any", model="RedHatAI/gemma-4-12B-it-FP8-Dynamic")
# Run inference
result = pipe("Your input here")
print(result)🏷️ Tags
transformerssafetensorsgemma4_unifiedimage-text-to-textfp8vllmllm-compressorcompressed-tensorsany-to-anybase_model:google/gemma-4-12B-itbase_model:quantized:google/gemma-4-12B-itlicense:apache-2.0endpoints_compatibleregion:us
More any-to-any Models
See all →🚀 Use This Model
Access model files, inference API, and full documentation on Hugging Face.
Open on Hugging Face →Browse Model Files ↗← Browse All Models🤖 Task: any-to-any
This model is designed for the any-to-any task. Explore more models for this use case.
All any-to-any Models →📊 Popularity
⬇ Downloads15.2K
❤️ Community Likes9
🛠️ Requirements
- →Install: pip install transformers
- →Python 3.8+ recommended for Transformers.
- →GPU (CUDA) speeds up inference significantly.
- →Use model.half() for fp16 on limited VRAM.