diff --git a/README.md b/README.md
index 36de9bced..d05a6e335 100644
--- a/README.md
+++ b/README.md
@@ -173,6 +173,14 @@ OpenLLM currently supports the following models. By default, OpenLLM doesn't inc
 
 ### Quickstart
 
+
+
+> **Note:** Baichuan requires to install with:
+> ```bash
+> pip install "openllm[baichuan]"
+> ```
+
+
 Run the following command to quickly spin up a Baichuan server:
 
 ```bash
@@ -244,6 +252,14 @@ openllm start baichuan-inc/baichuan-7b --backend pt
 
 ### Quickstart
 
+
+
+> **Note:** ChatGLM requires to install with:
+> ```bash
+> pip install "openllm[chatglm]"
+> ```
+
+
 Run the following command to quickly spin up a ChatGLM server:
 
 ```bash
@@ -365,6 +381,14 @@ openllm start databricks/dolly-v2-3b --backend pt
 
 ### Quickstart
 
+
+
+> **Note:** Falcon requires to install with:
+> ```bash
+> pip install "openllm[falcon]"
+> ```
+
+
 Run the following command to quickly spin up a Falcon server:
 
 ```bash
@@ -434,6 +458,14 @@ openllm start tiiuae/falcon-7b --backend pt
 
 ### Quickstart
 
+
+
+> **Note:** FlanT5 requires to install with:
+> ```bash
+> pip install "openllm[flan-t5]"
+> ```
+
+
 Run the following command to quickly spin up a FlanT5 server:
 
 ```bash
@@ -553,6 +585,14 @@ openllm start eleutherai/gpt-neox-20b --backend pt
 
 ### Quickstart
 
+
+
+> **Note:** Llama requires to install with:
+> ```bash
+> pip install "openllm[llama]"
+> ```
+
+
 Run the following command to quickly spin up a Llama server:
 
 ```bash
@@ -699,6 +739,14 @@ openllm start HuggingFaceH4/zephyr-7b-alpha --backend pt
 
 ### Quickstart
 
+
+
+> **Note:** MPT requires to install with:
+> ```bash
+> pip install "openllm[mpt]"
+> ```
+
+
 Run the following command to quickly spin up a MPT server:
 
 ```bash
@@ -771,6 +819,14 @@ openllm start mosaicml/mpt-7b --backend pt
 
 ### Quickstart
 
+
+
+> **Note:** OPT requires to install with:
+> ```bash
+> pip install "openllm[opt]"
+> ```
+
+
 Run the following command to quickly spin up a OPT server:
 
 ```bash
@@ -911,6 +967,14 @@ openllm start stabilityai/stablelm-tuned-alpha-3b --backend pt
 
 ### Quickstart
 
+
+
+> **Note:** StarCoder requires to install with:
+> ```bash
+> pip install "openllm[starcoder]"
+> ```
+
+
 Run the following command to quickly spin up a StarCoder server:
 
 ```bash
diff --git a/openllm-python/README.md b/openllm-python/README.md
index 36de9bced..d05a6e335 100644
--- a/openllm-python/README.md
+++ b/openllm-python/README.md
@@ -173,6 +173,14 @@ OpenLLM currently supports the following models. By default, OpenLLM doesn't inc
 
 ### Quickstart
 
+
+
+> **Note:** Baichuan requires to install with:
+> ```bash
+> pip install "openllm[baichuan]"
+> ```
+
+
 Run the following command to quickly spin up a Baichuan server:
 
 ```bash
@@ -244,6 +252,14 @@ openllm start baichuan-inc/baichuan-7b --backend pt
 
 ### Quickstart
 
+
+
+> **Note:** ChatGLM requires to install with:
+> ```bash
+> pip install "openllm[chatglm]"
+> ```
+
+
 Run the following command to quickly spin up a ChatGLM server:
 
 ```bash
@@ -365,6 +381,14 @@ openllm start databricks/dolly-v2-3b --backend pt
 
 ### Quickstart
 
+
+
+> **Note:** Falcon requires to install with:
+> ```bash
+> pip install "openllm[falcon]"
+> ```
+
+
 Run the following command to quickly spin up a Falcon server:
 
 ```bash
@@ -434,6 +458,14 @@ openllm start tiiuae/falcon-7b --backend pt
 
 ### Quickstart
 
+
+
+> **Note:** FlanT5 requires to install with:
+> ```bash
+> pip install "openllm[flan-t5]"
+> ```
+
+
 Run the following command to quickly spin up a FlanT5 server:
 
 ```bash
@@ -553,6 +585,14 @@ openllm start eleutherai/gpt-neox-20b --backend pt
 
 ### Quickstart
 
+
+
+> **Note:** Llama requires to install with:
+> ```bash
+> pip install "openllm[llama]"
+> ```
+
+
 Run the following command to quickly spin up a Llama server:
 
 ```bash
@@ -699,6 +739,14 @@ openllm start HuggingFaceH4/zephyr-7b-alpha --backend pt
 
 ### Quickstart
 
+
+
+> **Note:** MPT requires to install with:
+> ```bash
+> pip install "openllm[mpt]"
+> ```
+
+
 Run the following command to quickly spin up a MPT server:
 
 ```bash
@@ -771,6 +819,14 @@ openllm start mosaicml/mpt-7b --backend pt
 
 ### Quickstart
 
+
+
+> **Note:** OPT requires to install with:
+> ```bash
+> pip install "openllm[opt]"
+> ```
+
+
 Run the following command to quickly spin up a OPT server:
 
 ```bash
@@ -911,6 +967,14 @@ openllm start stabilityai/stablelm-tuned-alpha-3b --backend pt
 
 ### Quickstart
 
+
+
+> **Note:** StarCoder requires to install with:
+> ```bash
+> pip install "openllm[starcoder]"
+> ```
+
+
 Run the following command to quickly spin up a StarCoder server:
 
 ```bash
diff --git a/tools/update-readme.py b/tools/update-readme.py
index 6a57306e1..e8ef044bc 100755
--- a/tools/update-readme.py
+++ b/tools/update-readme.py
@@ -33,12 +33,13 @@ def main() -> int:
 
   for it in CONFIG_MAPPING.values():
     it = it()
-    details_block = ['<details>\n']
     architecture_name = it.__class__.__name__[:-6]
+    details_block = ['<details>\n', f'<summary>{architecture_name}</summary>\n\n', '### Quickstart\n']
+    if it['start_name'] in deps:
+      instruction = f'> ```bash\n> pip install "openllm[{it["start_name"]}]"\n> ```'
+      details_block.extend(markdown_noteblock(f'{architecture_name} requires to install with:\n{instruction}\n'))
     details_block.extend(
       [
-        f'<summary>{architecture_name}</summary>\n\n',
-        '### Quickstart\n',
         f'Run the following command to quickly spin up a {architecture_name} server:\n',
         f"""\
 ```bash