---
license: gemma  
inference: false    
base_model: google/gemma-7b-it    
base_model_relation: quantized  
tags:
- green
- p7
- llmware-chat
- ov
---

# gemma-7b-it-ov

**gemma-7b-it-ov** is an OpenVino int4 quantized version of Google's Gemma-7B with Instruct Training (IT), providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.    

[**gemma-7b-it-ov**](https://huggingface.co/google/gemma-7b-it) is a leading open source foundation chat model from Google.  


### Model Description

- **Developed by:** Google
- **Quantized by:** llmware
- **Model type:** gemma-7b  
- **Parameters:** 7 billion
- **Model Parent:** google/gemma-7b-it  
- **Language(s) (NLP):** English  
- **License:** Apache 2.0  
- **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)