---
title: jina-reranker-v3.5-mlx
canonical_url: "https://www.modelscope.ai/models/jinaai/jina-reranker-v3.5-mlx"
md_url: "https://www.modelscope.ai/models/jinaai/jina-reranker-v3.5-mlx.md"
repository: jinaai/jina-reranker-v3.5-mlx
last_updated: 2026-07-28
license: cc-by-nc-4.0
model_type:
  - qwen3
architectures:
  - JinaForRanking
base_model:
  - jinaai/jina-reranker-v3.5-exps
base_model_relation: finetune
parameters: 596.0M
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - multilingual
downloads: 133
stars: 0
tags:
  - reranker
  - mlx
  - apple-silicon
  - information-retrieval
---

# jina-reranker-v3.5-mlx

> jina-reranker-v3.5-mlx - An open-source model by jinaai on ModelScope. jina-reranker-v3.5-mlx

jinaai/jina-reranker-v3.5-mlx is a 596.0M-parameter machine learning model on ModelScope. licensed under cc-by-nc-4.0. derived from jinaai/jina-reranker-v3.5-exps.

- **Repository**: jinaai/jina-reranker-v3.5-mlx
- **License**: cc-by-nc-4.0
- **Parameters**: 596.0M
- **Base model**: jinaai/jina-reranker-v3.5-exps
- **Tags**: reranker, mlx, apple-silicon, information-retrieval
- **Downloads**: 133
- **Stars**: 0
- **Last updated**: 2026-07-28

Source: https://www.modelscope.ai/models/jinaai/jina-reranker-v3.5-mlx

---

# jina-reranker-v3.5-mlx

MLX port of [jina-reranker-v3.5](https://huggingface.co/jinaai/jina-reranker-v3.5), a domain-ready multilingual listwise reranker optimized for Apple Silicon. No transformers library required.

## Installation

```
pip install -r requirements.txt
```

## Usage

```python
from rerank import MLXReranker

reranker = MLXReranker()

query = "What are the health benefits of green tea?"
documents = [
    "Green tea contains antioxidants called catechins that may help reduce inflammation.",
    "Studies show that drinking green tea regularly can improve brain function.",
    "Basketball is one of the most popular sports in the United States.",
]

results = reranker.rerank(query, documents)
for result in results:
    print(f"Score: {result['relevance_score']:.4f}  {result['document'][:80]}...")
```

**Returns:** List of dicts sorted by relevance descending — `document`, `relevance_score`, `index`, and optionally `embedding` (shape `(512,)`).

```python
reranker.rerank(
    query: str,
    documents: List[str],
    top_n: Optional[int] = None,
    return_embeddings: bool = False,
)
```

### Custom Model Path

```python
reranker = MLXReranker(
    model_path="/path/to/jina-reranker-v3.5-mlx",
    projector_path="/path/to/jina-reranker-v3.5-mlx/projector.safetensors",
)
```

## Citation

If you find `jina-reranker-v3.5` useful in your research, please cite the [original paper](https://arxiv.org/abs/2607.18152):

```bibtex
@misc{nasika2026jinarerankerv35efficientlistwisereranker,
      title={jina-reranker-v3.5: An Efficient Listwise Reranker with Hybrid Attention and Self-Distillation}, 
      author={Christina Nasika and Feng Wang and Antonis Krasakis and Han Xiao},
      year={2026},
      eprint={2607.18152},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2607.18152}, 
}
```

## License

CC BY-NC 4.0. For commercial usage inquiries, please [contact Jina AI](https://jina.ai/contact-sales/).