This model is a int4 weight-only quantization with group_size 128 and symmetric quantization of Gryphe/Qwen3.6-35B-A3B-StyleTune generated by AutoRound. Please follow the license of the original model.

Quantization Details

Attribute	Value
Base Model	Gryphe/Qwen3.6-35B-A3B-StyleTune
Quantization Tool	AutoRound
Quantization Scheme	W4A16
Quantized Size	19504 MB

Evaluation Results

Task	Accuracy
hellaswag	0.6317
mmlu	0.8261
mmlu_abstract_algebra	0.5600
mmlu_anatomy	0.8444
mmlu_astronomy	0.9408
mmlu_business_ethics	0.8500
mmlu_clinical_knowledge	0.8906
mmlu_college_biology	0.9375
mmlu_college_chemistry	0.6400
mmlu_college_computer_science	0.7600
mmlu_college_mathematics	0.6500
mmlu_college_medicine	0.8266
mmlu_college_physics	0.6667
mmlu_computer_security	0.8500
mmlu_conceptual_physics	0.9404
mmlu_econometrics	0.8070
mmlu_electrical_engineering	0.8552
mmlu_elementary_mathematics	0.8095
mmlu_formal_logic	0.6984
mmlu_global_facts	0.4800
mmlu_high_school_biology	0.9452
mmlu_high_school_chemistry	0.8128
mmlu_high_school_computer_science	0.9000
mmlu_high_school_european_history	0.8606
mmlu_high_school_geography	0.9293
mmlu_high_school_government_and_politics	0.9741
mmlu_high_school_macroeconomics	0.8897
mmlu_high_school_mathematics	0.6296
mmlu_high_school_microeconomics	0.9580
mmlu_high_school_physics	0.8079
mmlu_high_school_psychology	0.9578
mmlu_high_school_statistics	0.7963
mmlu_high_school_us_history	0.8971
mmlu_high_school_world_history	0.8987
mmlu_human_aging	0.8206
mmlu_human_sexuality	0.8855
mmlu_humanities	0.7645
mmlu_international_law	0.9174
mmlu_jurisprudence	0.8704
mmlu_logical_fallacies	0.9080
mmlu_machine_learning	0.7768
mmlu_management	0.9029
mmlu_marketing	0.9487
mmlu_medical_genetics	0.8900
mmlu_miscellaneous	0.9387
mmlu_moral_disputes	0.8381
mmlu_moral_scenarios	0.6514
mmlu_nutrition	0.8791
mmlu_other	0.8552
mmlu_philosophy	0.8617
mmlu_prehistory	0.9105
mmlu_professional_accounting	0.7269
mmlu_professional_law	0.6675
mmlu_professional_medicine	0.9485
mmlu_professional_psychology	0.8889
mmlu_public_relations	0.7455
mmlu_security_studies	0.8367
mmlu_social_sciences	0.9067
mmlu_sociology	0.9353
mmlu_stem	0.8107
mmlu_us_foreign_policy	0.9400
mmlu_virology	0.5482
mmlu_world_religions	0.9240
piqa	0.8123

How to Use

HF Usage

Step 1: Install AutoRound

pip install auto-round

Step 2: Load and run the quantized model

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen3.6-35B-A3B-StyleTune-AutoRound-W4A16-RTN"

# 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

bash

vllm serve Qwen3.6-35B-A3B-StyleTune-AutoRound-W4A16-RTN \
    --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:

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.

LeaderboardModel1/Qwen3.6-35B-A3B-StyleTune-AutoRound-W4A16-RTN

Qwen3.6-35B-A3B-StyleTune-AutoRound-W4A16-RTN

Model Details