diff --git a/.github/workflows/vllm_ascend_test_nightly_a2.yaml b/.github/workflows/vllm_ascend_test_nightly_a2.yaml
index 72b97d41..d04c533e 100644
--- a/.github/workflows/vllm_ascend_test_nightly_a2.yaml
+++ b/.github/workflows/vllm_ascend_test_nightly_a2.yaml
@@ -108,8 +108,7 @@ jobs:
             model_list:
               - Qwen3-8B
               - Qwen2.5-VL-7B-Instruct
-              # TODO: This model has a bug that needs to be fixed and readded
-              # - Qwen2-Audio-7B-Instruct
+              - Qwen2-Audio-7B-Instruct
               - Qwen3-8B-W8A8
               - Qwen3-VL-8B-Instruct
               - Qwen2.5-Omni-7B
diff --git a/.github/workflows/vllm_ascend_test_report.yaml b/.github/workflows/vllm_ascend_test_report.yaml
index 0f7a0658..ec681f4a 100644
--- a/.github/workflows/vllm_ascend_test_report.yaml
+++ b/.github/workflows/vllm_ascend_test_report.yaml
@@ -64,8 +64,7 @@ jobs:
             model_list:
               - Qwen3-8B
               - Qwen2.5-VL-7B-Instruct
-              # TODO: This model has a bug that needs to be fixed and readded
-              # - Qwen2-Audio-7B-Instruct
+              - Qwen2-Audio-7B-Instruct
           - runner: linux-aarch64-a2-2
             model_list:
               - Qwen3-30B-A3B
diff --git a/tests/e2e/models/configs/Qwen2-Audio-7B-Instruct.yaml b/tests/e2e/models/configs/Qwen2-Audio-7B-Instruct.yaml
index 5c810ef4..2dd02ab4 100644
--- a/tests/e2e/models/configs/Qwen2-Audio-7B-Instruct.yaml
+++ b/tests/e2e/models/configs/Qwen2-Audio-7B-Instruct.yaml
@@ -8,3 +8,4 @@ tasks:
   - name: "exact_match,flexible-extract"
     value: 0.45
 num_fewshot: 5
+gpu_memory_utilization: 0.8