---
license: apache-2.0
inference: false 
tags: [green, llmware-rag, p1,ov]
---

# bling-qwen-500m-ov

<!-- Provide a quick summary of what the model is/does. -->

**bling-qwen-500m-ov** is an OpenVino int4 quantized version of BLING Qwen 500m, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.    

[**bling-qwen-500m**](https://huggingface.co/llmware/bling-qwen-500m) is a fact-based question-answering model, optimized for complex business documents.  

This is the smallest instruct trained model from the Qwen2 series, and offers reasonable accuracy given its small size.  For more accurate models, select a larger model in this series.  

### Model Description

- **Developed by:** llmware  
- **Model type:** qwen2  
- **Parameters:** 0.5 billion
- **Model Parent:** llmware/bling-qwen-500m  
- **Language(s) (NLP):** English  
- **License:** Apache 2.0  
- **Uses:** Fact-based question-answering  
- **RAG Benchmark Accuracy Score:** 81.0  
- **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)