diff --git a/vllm/config.py b/vllm/config.py
index 3139c5a08bfb..4fb2d95a5cee 100644
--- a/vllm/config.py
+++ b/vllm/config.py
@@ -228,6 +228,10 @@ def _init_multimodal_config(
         self, limit_mm_per_prompt: Optional[Mapping[str, int]]
     ) -> Optional["MultiModalConfig"]:
         architectures = getattr(self.hf_config, "architectures", [])
+
+        if len(architectures) == 0:
+            raise ValueError("No architectures found in the model config.")
+
         if any(
                 ModelRegistry.is_multimodal_model(arch)
                 for arch in architectures):
@@ -249,6 +253,8 @@ def _verify_tokenizer_mode(self) -> None:
 
     def _verify_embedding_mode(self) -> None:
         architectures = getattr(self.hf_config, "architectures", [])
+        if len(architectures) == 0:
+            raise ValueError("No architectures found in the model config.")
         self.embedding_mode = any(
             ModelRegistry.is_embedding_model(arch) for arch in architectures)
 
@@ -418,6 +424,8 @@ def verify_with_parallel_config(
 
         pipeline_parallel_size = parallel_config.pipeline_parallel_size
         architectures = getattr(self.hf_config, "architectures", [])
+        if len(architectures) == 0:
+            raise ValueError("No architectures found in the model config.")
         if not all(arch in _PP_SUPPORTED_MODELS
                    for arch in architectures) and pipeline_parallel_size > 1:
             raise NotImplementedError(