Qwen3-4B-GPT-5.2-High-Reasoning-Distill-qx86-hi-mlx

0.397,0.466,0.621,0.553,0.360,0.693,0.570

This model Qwen3-4B-GPT-5.2-High-Reasoning-Distill-qx86-hi-mlx was converted to MLX format from TeichAI/Qwen3-4B-GPT-5.2-High-Reasoning-Distill using mlx-lm version 0.30.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Qwen3-4B-GPT-5.2-High-Reasoning-Distill-qx86-hi-mlx")

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)