diff --git a/README.md b/README.md
index 2c36080..32dc00e 100644
--- a/README.md
+++ b/README.md
@@ -21,12 +21,9 @@
 
 ---
 
+## Run locally
 
-
----
-
-
-## Installation  
+**We recommand you use at least deepseek 14b, as smaller small will have trouble using tool and forget quickly the conversations.**
 
 ### 1️⃣ **Install Dependencies**  
 ```sh
@@ -65,8 +62,9 @@ Run the assistant:
 python3 main.py
 ```
 
-### 4️⃣ **Alternative: Run the LLM on your own server**  
+## **Alternative: Run the LLM on your own server**  
 
+### 1️⃣  **Set up and start the server scripts** 
 
 On your "server" that will run the AI model, get the ip address
 
@@ -80,6 +78,8 @@ Clone the repository and then, run the script `stream_llm.py` in `server/`
 python3 stream_llm.py
 ```
 
+### 2️⃣ **Run it** 
+
 Now on your personal computer:
 
 Clone the repository.