Update README.md

README.md

@@ -36,10 +36,6 @@ language:
 > [!NOTE]  
 > If you are using `llama.cpp`, use `--jinja` to enable the system prompt.
 >
-> ./llama.cpp/llama-cli -hf unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL --jinja --temp 0.7 --top-k -1 --top-p 0.95 -ngl 99
-> 
-> ollama run hf.co/unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL
-
 
 <div>
   <p style="margin-bottom: 0; margin-top: 0;">
@@ -62,6 +58,15 @@ language:
 <h1 style="margin-top: 0rem;">✨ How to Use Magistral:</h1>
 </div>
 
+Run in llama.cpp:
+```
+./llama.cpp/llama-cli -hf unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL --jinja --temp 0.7 --top-k -1 --top-p 0.95 -ngl 99
+```
+Run in Ollama:
+```
+ollama run hf.co/unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL
+```
+
 - Temperature of: 0.7
 - Set top_p to: 0.95
 - Max tokens (context length): 40,960 (32K + 8K)