Qwen3 14B 4bit AWQ

🚀 mlx-community/Qwen3-14B-4bit-AWQ

This project offers a model converted from Qwen/Qwen3-14B to the MLX format. It enables efficient text generation with the MLX framework.

🚀 Quick Start

Use with mlx

First, install the mlx-lm library:

pip install mlx-lm

Then, you can use the following Python code to generate text:

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen3-14B-4bit-AWQ")

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.