update readme

README.md

@@ -16,22 +16,22 @@ tags:
 
 <h1>A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone</h1>
 
-[GitHub](https://github.com/OpenBMB/MiniCPM-o) | [Demo](https://minicpm-v.openbmb.cn/)</a> 
+[GitHub](https://github.com/OpenBMB/MiniCPM-o) | [Demo](http://211.93.21.133:8889/)</a> 
 
 
 
 ## MiniCPM-V 4.0
 
-**MiniCPM-V 4.0** is the latest model in the MiniCPM-V series. The model is built in an end-to-end fasion based on SigLip2-400M and MiniCPM4-3B with a total of 4.1B parameters. It inherents the strong single-image, multi-image and video understanding performance of MiniCPM-V 2.6 with the efficiency largely improved. Notable features of MiniCPM-V 4.0 include:
+**MiniCPM-V 4.0** is the latest efficient model in the MiniCPM-V series. The model is built based on SigLIP2-400M and MiniCPM4-3B with a total of 4.1B parameters. It inherits the strong single-image, multi-image and video understanding performance of MiniCPM-V 2.6 with largely improved efficiency. Notable features of MiniCPM-V 4.0 include:
 
 - 🔥 **Leading Visual Capability.**
-  MiniCPM-V 4.0 achieves an average score of 69.0 on OpenCompass, a comprehensive evaluation of 8 popular benchmarks, outperforming both MiniCPM-V 2.6 (8.1B, 65.2) and Qwen2.5-VL-3B-Instruct (3.8B, 64.5). **With only 4.1B parameters, it surpasses the widely used proprietary model GPT-4.1-mini-20250414** for single image understanding.  It also outperforms MiniCPM-V 2.6 on both multi-image understanding and video understanding.
+   With only 4.1B parameters, MiniCPM-V 4.0 achieves an average score of 69.0 on OpenCompass, a comprehensive evaluation of 8 popular benchmarks, **outperforming GPT-4.1-mini-20250414, MiniCPM-V 2.6 (8.1B params, OpenCompass 65.2) and Qwen2.5-VL-3B-Instruct (3.8B params, OpenCompass 64.5)**. It also shows good performance in multi-image understanding and video understanding.
 
 - 🚀 **Superior Efficiency.**
-  Designed for performance on end devices, MiniCPM-V 4.0 runs smoothly on the **iPhone 16 Pro Max, devlivering 17.9 tokens/second decoding speed**. Compared to the already efficient MiniCPM-V 2.6, MiniCPM-V 4.0 further achieves a 30% throughput boost while offering enhanced visual understanding.
+  Designed for on-device deployment, MiniCPM-V 4.0 runs smoothly on end devices. For example, it devlivers **less than 2s first token delay and more than 17 token/s decoding on iPhone 16 Pro Max**, without heating problems. It also shows superior throughput under concurrent requests.
 
 -  💫  **Easy Usage.**
-  MiniCPM-V 4.0 can be easily used in various ways including **llama.cpp, Ollama, vLLM, SGLang, LLaMA-Factory and local web demo** etc. Get started easily with our **well-structured  [Cookbook](https://github.com/OpenSQZ/MiniCPM-V-CookBook)**, featuring detailed instructions and practical examples.
+  MiniCPM-V 4.0 can be easily used in various ways including **llama.cpp, Ollama, vLLM, SGLang, LLaMA-Factory and local web demo** etc. We also open-source iOS App that can run on iPhone and iPad. Get started easily with our well-structured [Cookbook](https://github.com/OpenSQZ/MiniCPM-V-CookBook), featuring detailed instructions and practical examples.
 
 
 ### Evaluation