Update README.md

README.md

@@ -19,6 +19,35 @@ Trained for enhanced general capabilities—including logic, coding, math, scien
 **Input**: Text prompts—questions, commands, code tasks—without any special thinking mode flags.  
 **Output**: Direct, context-aware responses—answers, explanations, code—with no internal thought annotations.
 
+---
+
+## How to use
+
+> ⚠️ **Hardware requirement:** the model currently runs **only on Qualcomm NPUs** (e.g., Snapdragon-powered AIPC).  
+> Apple NPU support is planned next.
+
+### 1) Install Nexa-SDK
+
+- Download and follow the steps under "Deploy Section" Nexa's model page:  [Download Windows arm64 SDK](https://sdk.nexa.ai/model/Qwen3-4B-Instruct-2507)
+- (Other platforms coming soon)
+
+### 2) Get an access token
+Create a token in the Model Hub, then log in:
+
+```bash
+nexa config set license '<access_token>'
+```
+
+### 3) Run the model
+Running:
+
+```bash
+nexa infer NexaAI/Qwen3-4B-Instruct-2507-npu
+```
+
+---
+
+
 ## License
 - Licensed under **Apache-2.0**