Qwen3 Embedding 4B 4bit DWQ

🚀 mlx-community/Qwen3-Embedding-4B-4bit-DWQ

This model is a feature extraction model that converts text into numerical vectors. It converts the Qwen/Qwen3-Embedding-4B model into the MLX format, enabling efficient feature extraction in the MLX framework.

🚀 Quick Start

This model mlx-community/Qwen3-Embedding-4B-4bit-DWQ was converted to MLX format from Qwen/Qwen3-Embedding-4B using mlx-lm version 0.24.0.

📦 Installation

pip install mlx-lm

💻 Usage Examples

Basic Usage

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen3-Embedding-4B-4bit-DWQ")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

📄 License

This project is under the Apache 2.0 license.