This model is a int4 weight-only quantization with group_size 128 and symmetric quantization of bottlecapai/ThinkingCap-Qwen3.6-27B generated by TUNING. Please follow the license of the original model.

Quantization Details

Attribute	Value
Base Model	bottlecapai/ThinkingCap-Qwen3.6-27B
Quantization Tool	TUNING
Quantization Scheme	W4A16
Quantized Size	18117 MB

Evaluation Results

Task	Accuracy
hellaswag	0.6376
mmlu	0.8459
mmlu_abstract_algebra	0.7300
mmlu_anatomy	0.8074
mmlu_astronomy	0.9408
mmlu_business_ethics	0.8200
mmlu_clinical_knowledge	0.8792
mmlu_college_biology	0.9514
mmlu_college_chemistry	0.6500
mmlu_college_computer_science	0.8300
mmlu_college_mathematics	0.7800
mmlu_college_medicine	0.8439
mmlu_college_physics	0.7059
mmlu_computer_security	0.8600
mmlu_conceptual_physics	0.9319
mmlu_econometrics	0.7719
mmlu_electrical_engineering	0.8414
mmlu_elementary_mathematics	0.8915
mmlu_formal_logic	0.8095
mmlu_global_facts	0.6000
mmlu_high_school_biology	0.9387
mmlu_high_school_chemistry	0.8325
mmlu_high_school_computer_science	0.9300
mmlu_high_school_european_history	0.8848
mmlu_high_school_geography	0.9394
mmlu_high_school_government_and_politics	0.9845
mmlu_high_school_macroeconomics	0.9359
mmlu_high_school_mathematics	0.6630
mmlu_high_school_microeconomics	0.9328
mmlu_high_school_physics	0.8146
mmlu_high_school_psychology	0.9431
mmlu_high_school_statistics	0.8704
mmlu_high_school_us_history	0.9412
mmlu_high_school_world_history	0.9494
mmlu_human_aging	0.8430
mmlu_human_sexuality	0.9084
mmlu_humanities	0.7994
mmlu_international_law	0.9174
mmlu_jurisprudence	0.8796
mmlu_logical_fallacies	0.9202
mmlu_machine_learning	0.7500
mmlu_management	0.8447
mmlu_marketing	0.9530
mmlu_medical_genetics	0.9500
mmlu_miscellaneous	0.9361
mmlu_moral_disputes	0.7775
mmlu_moral_scenarios	0.7508
mmlu_nutrition	0.9118
mmlu_other	0.8664
mmlu_philosophy	0.8424
mmlu_prehistory	0.8951
mmlu_professional_accounting	0.7837
mmlu_professional_law	0.7125
mmlu_professional_medicine	0.9228
mmlu_professional_psychology	0.8578
mmlu_public_relations	0.8182
mmlu_security_studies	0.8163
mmlu_social_sciences	0.9015
mmlu_sociology	0.9204
mmlu_stem	0.8408
mmlu_us_foreign_policy	0.9000
mmlu_virology	0.5663
mmlu_world_religions	0.9006
piqa	0.8134

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 = "ThinkingCap-Qwen3.6-27B-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

bash

vllm serve ThinkingCap-Qwen3.6-27B-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:

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/ThinkingCap-Qwen3.6-27B-AutoRound-W4A16-Tuning

ThinkingCap-Qwen3.6-27B-AutoRound-W4A16-Tuning

Model Details