diff --git a/tests/models/multimodal/generation/test_common.py b/tests/models/multimodal/generation/test_common.py
index 29680bafd50..e04d44d4be2 100644
--- a/tests/models/multimodal/generation/test_common.py
+++ b/tests/models/multimodal/generation/test_common.py
@@ -921,6 +921,7 @@ VLM_TEST_SETTINGS = {
         multi_image_prompt="Picture 1: <vlm_image>\nPicture 2: <vlm_image>\nDescribe these two images with one paragraph respectively.",  # noqa: E501
         max_model_len=4096,
         max_num_seqs=2,
+        num_logprobs=10,
         auto_cls=AutoModelForImageTextToText,
         vllm_output_post_proc=model_utils.qwen2_vllm_to_hf_output,
         image_size_factors=[(0.25,), (0.25, 0.25, 0.25), (0.25, 0.2, 0.15)],