Modelpublic

nightmedia/Qwen3-4B-Thinking-2507-GPT-5.1-Codex-Max-Distill-qx86-hi-mlx

sourceHugging Faceapache-2.0updated 9mo agoView on Hugging Face

0likes149downloads

Model Card

Qwen3-4B-Thinking-2507-GPT-5.1-Codex-Max-Distill-qx86-hi-mlx

0.417,0.503,0.648,0.564,0.376,0.713,0.576

This model Qwen3-4B-Thinking-2507-GPT-5.1-Codex-Max-Distill-qx86-hi-mlx was converted to MLX format from TeichAI/Qwen3-4B-Thinking-2507-GPT-5.1-Codex-Max-Distill using mlx-lm version 0.30.0.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("Qwen3-4B-Thinking-2507-GPT-5.1-Codex-Max-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)