Modelpublic

nhe-ai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled-mlx-8Bit

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face

0likes85downloads

Model Card

nhe-ai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled-mlx-8Bit

The Model nhe-ai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled-mlx-8Bit was converted to MLX format from nhe-ai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled using mlx-lm version 0.31.2.

—duplicated for compatibility from: khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("nhe-ai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled-mlx-8Bit")

prompt="hello"

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

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