Qwen3-24B-A4B-Freedom-HQ-Thinking-Abliterated-Heretic-mxfp4-mlx

0.440,0.546,0.764,0.595,0.376,0.723,0.578

This model Qwen3-24B-A4B-Freedom-HQ-Thinking-Abliterated-Heretic-mxfp4-mlx was converted to MLX format from DavidAU/Qwen3-24B-A4B-Freedom-HQ-Thinking-Abliterated-Heretic using mlx-lm version 0.30.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Qwen3-24B-A4B-Freedom-HQ-Thinking-Abliterated-Heretic-mxfp4-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)