diff --git a/tests/quantization/test_compressed_tensors.py b/tests/quantization/test_compressed_tensors.py
index 807b24d4e3aa..03480343d4bd 100644
--- a/tests/quantization/test_compressed_tensors.py
+++ b/tests/quantization/test_compressed_tensors.py
@@ -651,6 +651,7 @@ def test_compressed_tensors_2of4_sparse_compressed(vllm_runner, args_2of4):
         assert output
 
 
+@pytest.mark.skip(reason="Skip until the model config is updated")
 def test_compressed_tensors_nvfp4a16(vllm_runner):
     # run weight only example
     model = "nm-testing/TinyLlama-1.1B-Chat-v1.0-FP4"