Qwen3-0.6B-MLX-bf16-python-18k-alpaca/README.md

library_name, license, license_link, pipeline_tag, base_model, tags

library_name	license	license_link	pipeline_tag	base_model	tags
mlx	apache-2.0	https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE	text-generation	Qwen/Qwen3-0.6B-MLX-bf16	mlx

Austin362667/Qwen3-0.6B-MLX-bf16-python-18k-alpaca

This model Austin362667/Qwen3-0.6B-MLX-bf16-python-18k-alpaca was converted to MLX format from Qwen/Qwen3-0.6B-MLX-bf16 using mlx-lm version 0.31.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Austin362667/Qwen3-0.6B-MLX-bf16-python-18k-alpaca")

prompt = "hello"

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

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