README.md

metadata

library_name: mlx
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE
pipeline_tag: text-generation
base_model: Qwen/Qwen3-4B
tags:
  - mlx

mlx-community/Qwen3-4B-4bit-DWQ-calibration-1332

This model, mlx-community/Qwen3-4B-4bit-DWQ-calibration-1332, was converted to MLX format from Qwen/Qwen3-4B using the dataset mlx-community/qwen3_dwq_calibration_1332 with mlx-lm version 0.24.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen3-4B-4bit-DWQ-calibration-1332")

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)