Update README.md

README.md

@@ -20,7 +20,7 @@ quantized_by: bartowski
 
 **Model creator:** [mistralai](https://huggingface.co/mistralai)<br>
 **Original model**: [Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)<br>
-**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b3441](https://github.com/ggerganov/llama.cpp/releases/tag/b3441)<br>
+**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b3436](https://github.com/ggerganov/llama.cpp/releases/tag/b3436)<br>
 
 ## Model Summary:
 Mistral Nemo has a massive 1024000 (over 1 million) context window and supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash.<br>