diff --git a/README-zh-Hans.md b/README-zh-Hans.md
index f9ae0a2697b1..d34116125a44 100644
--- a/README-zh-Hans.md
+++ b/README-zh-Hans.md
@@ -150,6 +150,12 @@ Colossal-AI 为您提供了一系列并行组件。我们的目标是让您的
 
 - 用相同的硬件训练20倍大的模型
 
+<p id="GPT-2-NVME" align="center">
+<img  src="https://raw.githubusercontent.com/hpcaitech/public_assets/main/colossalai/img/GPT2-NVME.png" width=800/>
+</p>
+
+- 用相同的硬件训练120倍大的模型 (RTX 3080)
+
 ### PaLM
 <p id="PaLM-Single" align="center">
 <img  src="https://raw.githubusercontent.com/hpcaitech/public_assets/main/colossalai/img/PaLM-GPU1.png" width=450/>
diff --git a/README.md b/README.md
index 721a006571fb..172ce491ee70 100644
--- a/README.md
+++ b/README.md
@@ -155,6 +155,12 @@ Please visit our [documentation](https://www.colossalai.org/) and [examples](htt
 
 - 20x larger model size on the same hardware
 
+<p id="GPT-2-NVME" align="center">
+<img  src="https://raw.githubusercontent.com/hpcaitech/public_assets/main/colossalai/img/GPT2-NVME.png" width=800/>
+</p>
+
+- 120x larger model size on the same hardware (RTX 3080)
+
 ### PaLM
 <p id="PaLM-Single" align="center">
 <img  src="https://raw.githubusercontent.com/hpcaitech/public_assets/main/colossalai/img/PaLM-GPU1.png" width=450/>