diff --git a/vllm/model_executor/models/registry.py b/vllm/model_executor/models/registry.py
index 19153efd8e17..fc1de00906b3 100644
--- a/vllm/model_executor/models/registry.py
+++ b/vllm/model_executor/models/registry.py
@@ -152,6 +152,7 @@
     "Qwen2VLForConditionalGeneration": ("qwen2_vl", "Qwen2VLForConditionalGeneration"),  # noqa: E501
     # [Auto-converted (see adapters.py)]
     "Qwen2ForSequenceClassification": ("qwen2", "Qwen2ForCausalLM"),
+    "Qwen3ForSequenceClassification": ("qwen3", "Qwen3ForCausalLM"),
     # Technically PrithviGeoSpatialMAE is a model that works on images, both in
     # input and output. I am adding it here because it piggy-backs on embedding
     # models for the time being.