Qwen3.6-27B-AutoRound-MXFP4-RTN

Model Details

This model is a MXFP4 (Microscaling FP4) quantization of Qwen/Qwen3.6-27B generated by AutoRound. Please follow the license of the original model.

Quantization Details

Attribute	Value
Base Model	Qwen/Qwen3.6-27B
Quantization Tool	AutoRound
Quantization Scheme	MXFP4
Quantized Size	21231 MB

Evaluation Results

Task	Accuracy
hellaswag	0.6284
mmlu	0.8336
mmlu_abstract_algebra	0.7200
mmlu_anatomy	0.8000
mmlu_astronomy	0.9474
mmlu_business_ethics	0.8500
mmlu_clinical_knowledge	0.8906
mmlu_college_biology	0.9653
mmlu_college_chemistry	0.6500
mmlu_college_computer_science	0.7600
mmlu_college_mathematics	0.7000
mmlu_college_medicine	0.8671
mmlu_college_physics	0.7255
mmlu_computer_security	0.8200
mmlu_conceptual_physics	0.9277
mmlu_econometrics	0.7807
mmlu_electrical_engineering	0.8483
mmlu_elementary_mathematics	0.8783
mmlu_formal_logic	0.7460
mmlu_global_facts	0.6000
mmlu_high_school_biology	0.9516
mmlu_high_school_chemistry	0.8325
mmlu_high_school_computer_science	0.9100
mmlu_high_school_european_history	0.8364
mmlu_high_school_geography	0.9242
mmlu_high_school_government_and_politics	0.9741
mmlu_high_school_macroeconomics	0.9205
mmlu_high_school_mathematics	0.6370
mmlu_high_school_microeconomics	0.9370
mmlu_high_school_physics	0.8146
mmlu_high_school_psychology	0.9303
mmlu_high_school_statistics	0.8565
mmlu_high_school_us_history	0.9069
mmlu_high_school_world_history	0.9072
mmlu_human_aging	0.8072
mmlu_human_sexuality	0.8779
mmlu_humanities	0.7779
mmlu_international_law	0.9256
mmlu_jurisprudence	0.9167
mmlu_logical_fallacies	0.8896
mmlu_machine_learning	0.7500
mmlu_management	0.8835
mmlu_marketing	0.9188
mmlu_medical_genetics	0.9300
mmlu_miscellaneous	0.9246
mmlu_moral_disputes	0.7514
mmlu_moral_scenarios	0.7296
mmlu_nutrition	0.9052
mmlu_other	0.8600
mmlu_philosophy	0.8489
mmlu_prehistory	0.8796
mmlu_professional_accounting	0.7660
mmlu_professional_law	0.6884
mmlu_professional_medicine	0.9044
mmlu_professional_psychology	0.8627
mmlu_public_relations	0.7727
mmlu_security_studies	0.7959
mmlu_social_sciences	0.8944
mmlu_sociology	0.9204
mmlu_stem	0.8316
mmlu_us_foreign_policy	0.9500
mmlu_virology	0.5964
mmlu_world_religions	0.9006
piqa	0.8036

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 = "Qwen3.6-27B-AutoRound-MXFP4-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

vllm serve Qwen3.6-27B-AutoRound-MXFP4-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.