license: apache-2.0
library_name: transformers
tags:

• qwen
• qwen3.6
• moe
• multimodal
• vision
• uncensored
• fp16
• safetensors
• transformers
• mlx
• mlx-my-repo
  language:
• en
  base_model: khoi11/Qwen3.6-35B-A3B-Uncensored-HauhauCS-FP16

dolaloichua/Qwen3.6-35B-A3B-Uncensored-HauhauCS-FP16-mlx-8Bit

The Model dolaloichua/Qwen3.6-35B-A3B-Uncensored-HauhauCS-FP16-mlx-8Bit was converted to MLX format from khoi11/Qwen3.6-35B-A3B-Uncensored-HauhauCS-FP16 using mlx-lm version 0.31.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("dolaloichua/Qwen3.6-35B-A3B-Uncensored-HauhauCS-FP16-mlx-8Bit")

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)