diff --git a/optimum/intel/openvino/modeling.py b/optimum/intel/openvino/modeling.py
index 7831305d5f..357ca94c07 100644
--- a/optimum/intel/openvino/modeling.py
+++ b/optimum/intel/openvino/modeling.py
@@ -434,8 +434,8 @@ def _from_transformers(
         save_dir = TemporaryDirectory()
         save_dir_path = Path(save_dir.name)
 
-        # If load_in_8bit or quantization_config not specified then ov_config is set to None and will be set by default in convert depending on the model size
-        if load_in_8bit is None or not quantization_config:
+        # If load_in_8bit and quantization_config not specified then ov_config is set to None and will be set by default in convert depending on the model size
+        if load_in_8bit is None and not quantization_config:
             ov_config = None
         else:
             ov_config = OVConfig(dtype="fp32")
diff --git a/optimum/intel/openvino/modeling_base.py b/optimum/intel/openvino/modeling_base.py
index af00f7a06e..7ab99aab42 100644
--- a/optimum/intel/openvino/modeling_base.py
+++ b/optimum/intel/openvino/modeling_base.py
@@ -314,8 +314,8 @@ def _from_transformers(
         save_dir = TemporaryDirectory()
         save_dir_path = Path(save_dir.name)
 
-        # If load_in_8bit or quantization_config not specified then ov_config is set to None and will be set by default in convert depending on the model size
-        if load_in_8bit is None or not quantization_config:
+        # If load_in_8bit and quantization_config not specified then ov_config is set to None and will be set by default in convert depending on the model size
+        if load_in_8bit is None and not quantization_config:
             ov_config = None
         else:
             ov_config = OVConfig(dtype="fp32")
diff --git a/optimum/intel/openvino/modeling_base_seq2seq.py b/optimum/intel/openvino/modeling_base_seq2seq.py
index 3cb43e61b8..28e112c4d9 100644
--- a/optimum/intel/openvino/modeling_base_seq2seq.py
+++ b/optimum/intel/openvino/modeling_base_seq2seq.py
@@ -258,8 +258,8 @@ def _from_transformers(
             if use_cache:
                 task = task + "-with-past"
 
-        # If load_in_8bit or quantization_config not specified then ov_config is set to None and will be set by default in convert depending on the model size
-        if load_in_8bit is None or not quantization_config:
+        # If load_in_8bit and quantization_config not specified then ov_config is set to None and will be set by default in convert depending on the model size
+        if load_in_8bit is None and not quantization_config:
             ov_config = None
         else:
             ov_config = OVConfig(dtype="fp32")
diff --git a/optimum/intel/openvino/modeling_decoder.py b/optimum/intel/openvino/modeling_decoder.py
index 3d9671caf1..edc88d02cb 100644
--- a/optimum/intel/openvino/modeling_decoder.py
+++ b/optimum/intel/openvino/modeling_decoder.py
@@ -260,7 +260,7 @@ def _from_transformers(
             if use_cache:
                 task = task + "-with-past"
 
-        # If load_in_8bit or quantization_config not specified then ov_config is set to None and will be set by default in convert depending on the model size
+        # If load_in_8bit and quantization_config not specified then ov_config is set to None and will be set by default in convert depending on the model size
         if load_in_8bit is None and not quantization_config:
             ov_export_config = None
         else:
diff --git a/optimum/intel/openvino/modeling_diffusion.py b/optimum/intel/openvino/modeling_diffusion.py
index 5e8a0cdc59..a985f43d7c 100644
--- a/optimum/intel/openvino/modeling_diffusion.py
+++ b/optimum/intel/openvino/modeling_diffusion.py
@@ -321,8 +321,8 @@ def _from_transformers(
         save_dir = TemporaryDirectory()
         save_dir_path = Path(save_dir.name)
 
-        # If load_in_8bit or quantization_config not specified then ov_config is set to None and will be set by default in convert depending on the model size
-        if load_in_8bit is None or not quantization_config:
+        # If load_in_8bit and quantization_config not specified then ov_config is set to None and will be set by default in convert depending on the model size
+        if load_in_8bit is None and not quantization_config:
             ov_config = None
         else:
             ov_config = OVConfig(dtype="fp32")