Qwen3-VL-Reranker-8B-MLX-4bit

This is the MLX 4-bit quantized version of Qwen/Qwen3-VL-Reranker-8B, optimized for Apple Silicon (Mac / iPad / iPhone) inference using the MLX framework.

Quantization Info

Config	Value
Bits	4
Group Size	64
Quantization Mode	Affine
Dtype	bfloat16

Model Overview

• Model Type: MultiModal Reranker
• Supported Modalities: Text, images, screenshots, videos, and arbitrary multimodal combinations
• Parameters: 8B
• Context Length: 32k
• Languages: 30+

Requirements

pip install mlx-lm transformers

Usage with mlx-lm

from mlx_lm import load

model, tokenizer = load("Zeknes/Qwen3-VL-Reranker-8B-MLX-4bit")

For full usage examples (multimodal reranking, vLLM), please refer to the original model page: Qwen3-VL-Reranker-8B

Citation

@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}
}