Qwen3-VL-Reranker-8B

transformers>=4.57.0
qwen-vl-utils>=0.0.14
torch==2.8.0

from scripts.qwen3_vl_reranker import Qwen3VLReranker

# Specify the model path
model_name_or_path = "Qwen/Qwen3-VL-Reranker-8B"

# Initialize the Qwen3VLEmbedder model
model = Qwen3VLReranker(model_name_or_path=model_name_or_path)
# We recommend enabling flash_attention_2 for better acceleration and memory saving,
# model = Qwen3VLReranker(model_name_or_path=model_name_or_path, torch_dtype=torch.bfloat16, attn_implementation="flash_attention_2")
# Combine queries and documents into a single input list

inputs = {
    "instruction": "Retrieval relevant image or text with user's query",
    "query": {"text": "A woman playing with her dog on a beach at sunset."},
    "documents": [
        {"text": "A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust."},
        {"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"},
        {"text": "A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust.", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"}
    ],
    "fps": 1.0
}

scores = model.process(inputs)
print(scores)
# [0.7838293313980103, 0.585621178150177, 0.6147719025611877]

@article{qwen3vlembedding,
  title={Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking},
  author={Li, Mingxin and Zhang, Yanzhao and Long, Dingkun and Chen Keqin and Song, Sibo and Bai, Shuai and Yang, Zhibo and Xie, Pengjun and Yang, An and Liu, Dayiheng and Zhou, Jingren and Lin, Junyang},
  journal={arXiv preprint arXiv:2601.04720},
  year={2026}
}