Qwen3 4B 4bit DWQ

🚀 mlx-community/Qwen3-4B-4bit-DWQ

This project focuses on converting the model Qwen/Qwen3-4B into the MLX format, resulting in mlx-community/Qwen3-4B-4bit-DWQ. The conversion process is carried out using mlx-lm version 0.24.1.

🚀 Quick Start

📦 Installation

To use this model, you need to install the mlx-lm library first. You can install it using the following command:

pip install mlx-lm

💻 Usage Examples

Basic Usage

Here is a basic example of using the converted model:

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen3-4B-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 licensed under the Apache 2.0 License.