Modelpublic

sealad886/DavidAU-Qwen3.6-21B-IQ-Ultra-Heretic-Uncensored-Thinking-mixed_2_6-MLX

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

1likes647downloads

Model Card

sealad886/DavidAU-Qwen3.6-21B-IQ-Ultra-Heretic-Uncensored-Thinking-mixed26-MLX

This model sealad886/DavidAU-Qwen3.6-21B-IQ-Ultra-Heretic-Uncensored-Thinking-mixed_2_6-MLX was converted to MLX format from DavidAU/Qwen3.6-21B-IQ-Ultra-Heretic-Uncensored-Thinking using mlx-lm version 0.31.1.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("sealad886/DavidAU-Qwen3.6-21B-IQ-Ultra-Heretic-Uncensored-Thinking-mixed_2_6-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)