---
license: gemma
inference: false
base_model: google/gemma-3-4b
base_model_relation: quantized 
tags:
- green
- p4
- llmware-chat
- openvino
---

# gemma-3-4b-it-ov-int4-fq

**gemma-3-4b-it-ov-int4-fq** is an int4 OpenVINO quantized version of Google's Gemma-3-4B with Instruct Training (IT), providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.    

[**gemma-3-4b**](https://huggingface.co/google/gemma-3-4b) is a leading open source foundation model from Google.  


### Model Description

- **Developed by:** Google  
- **Model type:** gemma-3  
- **Parameters:** 4 billion  
- **Model Parent:** google/gemma-4b-it  
- **Language(s) (NLP):** English  
- **License:** gemma license
- **Uses:** General purpose chat 
- **RAG Benchmark Accuracy Score:** NA  
- **Quantization:** int4  
  

## Model Card Contact

[llmware on github](https://www.github.com/llmware-ai/llmware)  

[llmware on hf](https://www.huggingface.co/llmware)  

[llmware website](https://www.llmware.ai)