---
license: gemma
inference: false
base_model: google/gemma-2b-it
base_model_relation: quantized 
tags:
- green
- p2
- llmware-chat
- onnx
---

# gemma-2b-it-onnx

**gemma-2b-it-onnx** is an ONNX int4 quantized version of Google's Gemma-2B with Instruct Training (IT), providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.    

[**gemma-2b-it**](https://huggingface.co/google/gemma-2b-it) is a leading open source foundation model from Google.  


### Model Description

- **Developed by:** Google
- **Quantized by:** llmware
- **Model type:** gemma-2b  
- **Parameters:** 2 billion
- **Model Parent:** google/gemma-2b-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)