Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-AutoRound-W4A16-Tuning

Model Details

This model is a int4 weight-only quantization with group_size 128 and symmetric quantization of DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking generated by TUNING. Please follow the license of the original model.

Quantization Details

Attribute	Value
Base Model	DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking
Quantization Tool	TUNING
Quantization Scheme	W4A16
Quantized Size	23884 MB

Evaluation Results

Task	Accuracy
hellaswag	0.6439
mmlu	0.8446
mmlu_abstract_algebra	0.7200
mmlu_anatomy	0.8444
mmlu_astronomy	0.9276
mmlu_business_ethics	0.8300
mmlu_clinical_knowledge	0.8755
mmlu_college_biology	0.9514
mmlu_college_chemistry	0.6600
mmlu_college_computer_science	0.8100
mmlu_college_mathematics	0.7500
mmlu_college_medicine	0.8671
mmlu_college_physics	0.7255
mmlu_computer_security	0.8600
mmlu_conceptual_physics	0.9404
mmlu_econometrics	0.8158
mmlu_electrical_engineering	0.8276
mmlu_elementary_mathematics	0.8254
mmlu_formal_logic	0.7857
mmlu_global_facts	0.5600
mmlu_high_school_biology	0.9581
mmlu_high_school_chemistry	0.7833
mmlu_high_school_computer_science	0.9300
mmlu_high_school_european_history	0.8788
mmlu_high_school_geography	0.9444
mmlu_high_school_government_and_politics	0.9896
mmlu_high_school_macroeconomics	0.9179
mmlu_high_school_mathematics	0.5926
mmlu_high_school_microeconomics	0.9496
mmlu_high_school_physics	0.8344
mmlu_high_school_psychology	0.9486
mmlu_high_school_statistics	0.8519
mmlu_high_school_us_history	0.9461
mmlu_high_school_world_history	0.9325
mmlu_human_aging	0.8386
mmlu_human_sexuality	0.9160
mmlu_humanities	0.8011
mmlu_international_law	0.9339
mmlu_jurisprudence	0.8889
mmlu_logical_fallacies	0.9202
mmlu_machine_learning	0.7768
mmlu_management	0.8932
mmlu_marketing	0.9444
mmlu_medical_genetics	0.9300
mmlu_miscellaneous	0.9387
mmlu_moral_disputes	0.8468
mmlu_moral_scenarios	0.7687
mmlu_nutrition	0.8987
mmlu_other	0.8674
mmlu_philosophy	0.8617
mmlu_prehistory	0.8827
mmlu_professional_accounting	0.7801
mmlu_professional_law	0.6943
mmlu_professional_medicine	0.9449
mmlu_professional_psychology	0.8742
mmlu_public_relations	0.7455
mmlu_security_studies	0.8163
mmlu_social_sciences	0.9071
mmlu_sociology	0.9353
mmlu_stem	0.8262
mmlu_us_foreign_policy	0.9400
mmlu_virology	0.5663
mmlu_world_religions	0.8889
piqa	0.7992

How to Use

HF Usage

Step 1: Install AutoRound

pip install auto-round

Step 2: Load and run the quantized model

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-AutoRound-W4A16-Tuning"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")

# prepare the model input
prompt = "Write a quick sort algorithm."
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(**model_inputs, max_new_tokens=512)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :].tolist()

content = tokenizer.decode(output_ids, skip_special_tokens=True)
print("content:", content)

VLLM Usage

vllm serve Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-AutoRound-W4A16-Tuning \
    --trust-remote-code \
    --dtype bfloat16 \
    --tensor_parallel_size 1

If you encounter any issues, feel free to open an issue on the AutoRound GitHub repo or provide feedback on the Low-Bit Open LLM Leaderboard.

Ethical Considerations and Limitations

The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs. Therefore, before deploying any applications of the model, developers should perform safety testing.

Caveats and Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Here are a couple of useful links to learn more about Intel's AI software:

• Intel Neural Compressor
• AutoRound

Disclaimer

The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.

Cite

@article{cheng2023optimize,
  title={Optimize weight rounding via signed gradient descent for the quantization of llms},
  author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi},
  journal={arXiv preprint arXiv:2309.05516},
  year={2023}
}

arxiv github

---

This model is part of the Intel Low-Bit Open LLM Leaderboard initiative.