Update README.md

README.md

@@ -117,7 +117,7 @@ print(res)
 Please look at [GitHub](https://github.com/OpenBMB/MiniCPM-V) for more detail about usage.
 
 ## Int4 quantized version
-Download the int4 quantized version for lower GPU memory usage:  [MiniCPM-Llama3-V-2_5-int4](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-int4).
+Download the int4 quantized version for lower GPU memory (8GB) usage:  [MiniCPM-Llama3-V-2_5-int4](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-int4).
 
 ## MiniCPM-V 2.0 <!-- omit in toc -->
 Please see the info about MiniCPM-V 2.0 [here](https://huggingface.co/openbmb/MiniCPM-V-2).