license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE language:

• en
• zh
• ru
• es
• fr
• it
• ja
• ko
• af
• de
• ar
• tr
• is
• pl
• sw
• sv
• nl
• he
• id
• uk
• fa
• pa
• pt
• ms
• fi
• el base_model: TheCluster/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-MLX-mixed-9.4bit library_name: mlx tags:
• heretic
• abliterated
• uncensored
• decensored
• 9bit
• mixed-precision
• fine tune
• creative
• creative writing
• fiction writing
• plot generation
• sub-plot generation
• story generation
• scene continue
• storytelling
• fiction story
• science fiction
• romance
• all genres
• story
• writing
• vivid prosing
• vivid writing
• fiction
• roleplaying
• all use cases
• mlx
• mlx-my-repo pipeline_tag: image-text-to-text

culturerevolt/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-MLX-mixed-9.4bit-mlx-4Bit

The Model culturerevolt/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-MLX-mixed-9.4bit-mlx-4Bit was converted to MLX format from TheCluster/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-MLX-mixed-9.4bit using mlx-lm version 0.31.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("culturerevolt/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-MLX-mixed-9.4bit-mlx-4Bit")

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)