library_name: mlx
license: apache-2.0
license_link: https://huggingface.co/Jackrong/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled/blob/main/LICENSE
pipeline_tag: text-generation
base_model: huihui-ai/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated
tags:

• abliterated
• uncensored
• Claude
• reasoning
• chain-of-thought
• Dense
• mlx

mlx-community/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-5bit

This model mlx-community/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-5bit was
converted to MLX format from huihui-ai/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated
using mlx-lm version 0.31.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-5bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)