library_name: mlx
license: "apache-2.0"
pipeline_tag: text-generation
language:
- en
- ko
- zh
- ja
tags: - mlx
- "mlx-8bit"
- quantized
- safetensors
- apple-silicon
- Qwen
- Qwen3.6
- Qwen3_5_moe
- reasoning
- distillation
- chain-of-thought
- mixture-of-experts
- moe
- lora
- unsloth
- abliterated
- uncensored
datasets: - lordx64/reasoning-distill-opus-4-7-max-sft
base_model: - huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated
model-index: []
🌌 huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated converted to MLX 8-bit
About This Quantization
Apple Sllicon / MLX 8-bit
- Source Model (BF16) : huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated
- Quantized By: @nabi-chan
Quickstart
Install
pip install -U "mlx-lm>=0.31.2"
Python
from mlx_lm import load, generate
model, tokenizer = load("nabi-chan/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-MLX-8bit")
print(generate(model, tokenizer, prompt="Explain quantum entanglement simply.", max_tokens=128))
CLI
python3 -m mlx_lm generate \
--model nabi-chan/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-MLX-8bit \
--prompt "Write a haiku about Apple Silicon." \
--max-tokens 128
Quantization Details
| Property | Value |
|---|---|
| Method | MLX affine quantization |
| Bits / weight | 8 |
| Group size | 64 |
| Non-quant dtype | bfloat16 |
| Quantizer version | mlx : 0.31.2 / mlx-lm : 0.31.3 / mlx-vlm: 0.4.4 |
[!WARNING]
Protected tensors keep their original dtype. In VLM models, vision tensors and some guarded layers may remain unquantized.
Everything below is huihui-ai's original model card, preserved verbatim.
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated
This is an uncensored version of lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
ollama
Please use the latest version of ollama
You can use huihui_ai/qwen3.6-abliterated:35b-Claude-4.7 directly,
ollama run huihui_ai/Qwen3.6-abliterated:35b-Claude-4.7
Usage Warnings
Risk of Sensitive or Controversial Outputs: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.
Not Suitable for All Audiences: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.
Legal and Ethical Responsibilities: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.
Research and Experimental Use: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.
Monitoring and Review Recommendations: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.
No Default Safety Guarantees: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.
Donation
Your donation helps us continue our further development and improvement, a cup of coffee can do it.
- bitcoin:
bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
- Support our work on Ko-fi!