README.md

---
license: apache-2.0
library_name: transformers
pipeline_tag: text-ranking
base_model:
- Qwen/Qwen3-VL-2B-Instruct
tags:
- transformers
- multimodal rerank
- text rerank
- mlx
---

# mlx-community/Qwen3-VL-Reranker-2B-4bit

The Model [mlx-community/Qwen3-VL-Reranker-2B-4bit](https://huggingface.co/mlx-community/Qwen3-VL-Reranker-2B-4bit) was converted to MLX format from [Qwen/Qwen3-VL-Reranker-2B](https://huggingface.co/Qwen/Qwen3-VL-Reranker-2B) using mlx-lm version **0.1.0**.

## Use with mlx

```bash
pip install mlx-embeddings
```

```python
from mlx_embeddings import load, generate
import mlx.core as mx

model, tokenizer = load("mlx-community/Qwen3-VL-Reranker-2B-4bit")

# For image-text embeddings
images = [
    "./images/cats.jpg",  # cats
]
texts = ["a photo of cats", "a photo of a desktop setup", "a photo of a person"]

# Process all image-text pairs
outputs = generate(model, processor, texts, images=images)
logits_per_image = outputs.logits_per_image
probs = mx.sigmoid(logits_per_image) # probabilities for this image
for i, image in enumerate(images):
    print(f"Image {i+1}:")
    for j, text in enumerate(texts):
        print(f"  {probs[i][j]:.1%} match with '{text}'")
    print()


```