---
license: llama3
inference: false
tags:
- green
- p8
- llmware-chat
- ov
---

# dolphin-2.9.4-llama-3.1-8b-ov

**dolphin-2.9.4-llama-3.1-8b-ov** is an OpenVino int4 quantized version of dolphin-2.9.4-llama-3.1-8b-ov, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.    

[**dolphin-2.9.4-llama-3.1-8b**](https://huggingface.co/cognitivecomputations/dolphin-2.9.4-llama-3.1-8b) is a leading open source Dolphin fine-tuned model on top of Llama 3.1 base.



### Model Description

- **Developed by:** cognitive computations
- **Quantized by:** llmware  
- **Model type:** llama-3.1 
- **Parameters:** 8 billion
- **Model Parent:** cognitivecomputations/dolphin-2.9.4-llama-3.1-8b  
- **Language(s) (NLP):** English  
- **License:** Llama 3.1 Community License
- **Uses:** General chat use cases 
- **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)