license: apache-2.0 base_model: DavidAU/Qwen3-48B-A4B-Savant-Commander-Distill-12X-Closed-Open-Heretic-Uncensored tags:

• 256k context
• Qwen3
• Mixture of Experts
• MOE
• MOE Dense
• thinking
• reasoning
• GPT-5.1-High-Reasoning-Distill
• Gemini-3-Pro-Preview-High-Reasoning-Distill
• Claude-4.5-Opus-High-Reasoning-Distill
• Claude-Sonnet-4-Reasoning-Distill
• Kimi-K2-Thinking-Distill
• Gemini-2.5-Flash-Distill
• Gemini-2.5-Flash-Lite-Preview-Distill
• gpt-oss-120b-Distill
• GLM-Flash-4.6-Distill
• Open-R1-Distill
• Command-A-Reasoning-Distill
• 2 experts
• 4Bx12
• All use cases
• bfloat16
• heretic
• uncensored
• decensored
• abliterated
• merge
• 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
• not-for-all-audiences
• mlx
• mlx-my-repo pipeline_tag: text-generation language:
• en library_name: transformers

culturerevolt/Qwen3-48B-A4B-Savant-Commander-Distill-12X-Closed-Open-Heretic-Uncensored-mlx-2Bit

The Model culturerevolt/Qwen3-48B-A4B-Savant-Commander-Distill-12X-Closed-Open-Heretic-Uncensored-mlx-2Bit was converted to MLX format from DavidAU/Qwen3-48B-A4B-Savant-Commander-Distill-12X-Closed-Open-Heretic-Uncensored using mlx-lm version 0.31.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("culturerevolt/Qwen3-48B-A4B-Savant-Commander-Distill-12X-Closed-Open-Heretic-Uncensored-mlx-2Bit")

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)