pip install mlx mlx-lm
mlx_lm.convert --hf-path sm54/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B -q --q-bits 8 --upload-repo litmudoc/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-MLX-Q8

Use with mlx

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("litmudoc/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-MLX-Q8")

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)