diff --git a/tests/quantization/test_torchao.py b/tests/quantization/test_torchao.py
index c859f890b..fb794baa5 100644
--- a/tests/quantization/test_torchao.py
+++ b/tests/quantization/test_torchao.py
@@ -20,7 +20,7 @@ TORCHAO_AVAILABLE = importlib.util.find_spec("torchao") is not None
 @pytest.mark.skipif(not TORCHAO_AVAILABLE, reason="torchao is not available")
 def test_pre_quantized_model(vllm_runner):
     with vllm_runner(
-        "drisspg/fp8-opt-125m",
+        "torchao-testing/opt-125m-Float8WeightOnlyConfig-v2-0.15.0",
         quantization="torchao",
         dtype="bfloat16",
         enforce_eager=True,
@@ -52,22 +52,6 @@ def test_opt_125m_int8wo_model_loading_with_params(vllm_runner, pt_load_map_loca
         assert output
 
 
-@pytest.mark.skipif(not TORCHAO_AVAILABLE, reason="torchao is not available")
-def test_opt_125m_int4wo_model_per_module_quant(vllm_runner):
-    torch._dynamo.reset()
-    model_name = "jerryzh168/opt-125m-int4wo-per-module"
-    with vllm_runner(
-        model_name=model_name,
-        quantization="torchao",
-        dtype="bfloat16",
-        pt_load_map_location="cuda:0",
-        enforce_eager=True,
-    ) as llm:
-        output = llm.generate_greedy(["The capital of France is"], max_tokens=4)
-
-        assert output
-
-
 @pytest.mark.skipif(not TORCHAO_AVAILABLE, reason="torchao is not available")
 def test_qwenvl_int8wo_model_loading_with_params(vllm_runner):
     torch._dynamo.reset()