license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507/blob/main/LICENSE
language:
- en
base_model: huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated
pipeline_tag: text-generation
library_name: transformers
tags: - abliterated
- uncensored
- mlx
- mlx-my-repo
cs2764/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-mlx-6Bit-gs32
The Model cs2764/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-mlx-6Bit-gs32 was converted to MLX format from huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated using mlx-lm version 0.26.2.
Quantization Details
This model was converted with the following quantization settings:
- Quantization Strategy: 6-bit quantization
- Group Size: 32
- Average bits per weight: 7.000
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("cs2764/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-mlx-6Bit-gs32")
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)