Qwen3 8B 4bit AWQ

🚀 mlx-community/Qwen3-8B-4bit-AWQ

This project focuses on the mlx-community/Qwen3-8B-4bit-AWQ model. It converts the Qwen/Qwen3-8B model into the MLX format using the mlx-lm version 0.24.0, enabling efficient text generation tasks.

🚀 Quick Start

Prerequisites

Make sure you have pip installed in your Python environment.

Installation

pip install mlx-lm

Usage

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen3-8B-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.