# MiniCPM-V Best Practices

**MiniCPM-V** is a series of end-side multimodal LLMs (MLLMs) designed for vision-language understanding. The models take image, video and text as inputs and provide high-quality text output, aiming to achieve **strong performance and efficient deployment**. The most notable models in this series currently include MiniCPM-Llama3-V 2.5 and MiniCPM-V 2.6. The following sections provide detailed tutorials and guidance for each version of the MiniCPM-V models.


## MiniCPM-V 2.6

MiniCPM-V 2.6 is the latest and most capable model in the MiniCPM-V series. With a total of 8B parameters, the model **surpasses GPT-4V in single image, multi-image and video understanding**. It outperforms **GPT-4o mini, Gemini 1.5 Pro and Claude 3.5 Sonnet** in single image understanding, and advances MiniCPM-Llama3-V 2.5's features such as strong OCR capability, trustworthy behavior, multilingual support, and end-side deployment. Due to its superior token density, MiniCPM-V 2.6 can for the first time support real-time video understanding on end-side devices such as iPad.

* [Deployment Tutorial](https://modelbest.feishu.cn/wiki/C2BWw4ZP0iCDy7kkCPCcX2BHnOf)
* [Training Tutorial](https://modelbest.feishu.cn/wiki/GeHMwLMa0i2FhUkV0f6cz3HWnV1)
* [Quantization Tutorial](https://modelbest.feishu.cn/wiki/YvsPwnPwWiqUjlkmW0scQ76TnBb)

## MiniCPM-Llama3-V 2.5

MiniCPM-Llama3-V 2.5 is built on SigLip-400M and Llama3-8B-Instruct with a total of 8B parameters. It exhibits a significant performance improvement over MiniCPM-V 2.0.

* [Quantization Tutorial](https://modelbest.feishu.cn/wiki/Kc7ywV4X1ipSaAkuPFOc9SFun8b)
* [Training Tutorial](https://modelbest.feishu.cn/wiki/UpSiw63o9iGDhIklmwScX4a6nhW)
* [End-side Deployment](https://modelbest.feishu.cn/wiki/Lwr9wpOQdinr6AkLzHrc9LlgnJD)
* [Deployment Tutorial](https://modelbest.feishu.cn/wiki/LTOKw3Hz7il9kGkCLX9czsennKe)
* [HD Decoding Tutorial](https://modelbest.feishu.cn/wiki/Ug8iwdXfhiHVsDk2gGEco6xnnVg)
* [Model Structure](https://modelbest.feishu.cn/wiki/ACtAw9bOgiBQ9lkWyafcvtVEnQf)