diff --git a/.github/workflows/vllm_ascend_test.yaml b/.github/workflows/vllm_ascend_test.yaml
index 515086a8f0..795ddd0168 100644
--- a/.github/workflows/vllm_ascend_test.yaml
+++ b/.github/workflows/vllm_ascend_test.yaml
@@ -208,6 +208,7 @@ jobs:
             VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeekV3_dbo
             VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py::test_models_distributed_QwQ_with_flashcomm_v1
             VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_with_flashcomm_v2
+            VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3MoE_W8A8
             VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/ --ignore=tests/multicard/test_ilama_lora_tp2.py --ignore=tests/multicard/test_offline_inference_distributed.py --ignore=tests/multicard/test_w4a8_deepseek.py
           fi
 
diff --git a/tests/multicard/test_offline_inference_distributed.py b/tests/multicard/test_offline_inference_distributed.py
index 7593a4afd7..d3b7155ae1 100644
--- a/tests/multicard/test_offline_inference_distributed.py
+++ b/tests/multicard/test_offline_inference_distributed.py
@@ -227,4 +227,21 @@ def test_models_distributed_Qwen3_with_flashcomm_v2():
             dtype="auto",
             tensor_parallel_size=2,
     ) as vllm_model:
-        vllm_model.generate_greedy(example_prompts, max_tokens)
\ No newline at end of file
+        vllm_model.generate_greedy(example_prompts, max_tokens)
+
+
+def test_models_distributed_Qwen3MoE_W8A8():
+    example_prompts = [
+        "Hello, my name is",
+    ]
+    max_tokens = 5
+
+    with VllmRunner(
+            snapshot_download("vllm-ascend/Qwen3-30B-A3B-W8A8"),
+            max_model_len=8192,
+            enforce_eager=True,
+            dtype="auto",
+            tensor_parallel_size=2,
+            quantization="ascend",
+    ) as vllm_model:
+        vllm_model.generate_greedy(example_prompts, max_tokens)