This is the MLX 4-bit quantized version of Qwen/Qwen3-VL-Embedding-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 Embedding
Supported Modalities: Text, images, screenshots, videos, and arbitrary multimodal combinations
Parameters: 8B
Context Length: 32k
Embedding Dimension: Up to 4096 (supports custom dimensions from 64 to 4096)
Languages: 30+

Requirements

pip install mlx-lm transformers

Usage with `mlx-lm`

python

from mlx_lm import load

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

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

Citation

bibtex

@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}
}

Zeknes/Qwen3-VL-Embedding-8B-MLX-4bit

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

Quantization Info

Model Overview

Requirements

Usage with mlx-lm

Citation

Zeknes/
Qwen3-VL-Embedding-8B-MLX-4bit

Usage with `mlx-lm`