CoolFace
Modelpublic

vadimayegorov/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-mixed_2_6-mlx-fp16

sourceHugging Faceapache-2.0updated 24d agoView on Hugging Face
0likes462downloads
Model Card

vadimayegorov/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-mixed26-mlx-fp16

The Model vadimayegorov/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-mixed_2_6-mlx-fp16 was converted to MLX format from zecanard/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-mixed_2_6 using mlx-lm version 0.31.2.

Use with mlx

bash
pip install mlx-lm
python
from mlx_lm import load, generate

model, tokenizer = load("vadimayegorov/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-mixed_2_6-mlx-fp16")

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)