diff --git a/python/llm/src/ipex_llm/transformers/convert.py b/python/llm/src/ipex_llm/transformers/convert.py
index 168a83ab..b89320f8 100644
--- a/python/llm/src/ipex_llm/transformers/convert.py
+++ b/python/llm/src/ipex_llm/transformers/convert.py
@@ -822,7 +822,7 @@ def ggml_convert_low_bit(model, qtype, optimize_model=True,
     if optimize_model:
         model = _optimize_post(model, lightweight_bmm)
 
-    if hasattr(model, "config") and \
+    if hasattr(model, "config") and hasattr(model.config, "model_type") and \
             model.config.model_type == "qwen" and hasattr(model.config, "visual"):
         # for Qwen-VL-Chat
         # Due to issue https://github.com/intel/intel-extension-for-pytorch/issues/454,