This model is a MXFP4 (Microscaling FP4) quantization of ConicCat/Qwen3.5-27B-Writer-V2 generated by AutoRound. Please follow the license of the original model.

Quantization Details

Attribute	Value
Base Model	ConicCat/Qwen3.5-27B-Writer-V2
Quantization Tool	AutoRound
Quantization Scheme	MXFP4
Quantized Size	20421 MB

Evaluation Results

Task	Accuracy
hellaswag	0.6525
mmlu	0.8391
mmlu_abstract_algebra	0.7300
mmlu_anatomy	0.8296
mmlu_astronomy	0.9605
mmlu_business_ethics	0.8600
mmlu_clinical_knowledge	0.8792
mmlu_college_biology	0.9653
mmlu_college_chemistry	0.6600
mmlu_college_computer_science	0.8200
mmlu_college_mathematics	0.6800
mmlu_college_medicine	0.8092
mmlu_college_physics	0.8137
mmlu_computer_security	0.8600
mmlu_conceptual_physics	0.9191
mmlu_econometrics	0.7281
mmlu_electrical_engineering	0.8345
mmlu_elementary_mathematics	0.8862
mmlu_formal_logic	0.6984
mmlu_global_facts	0.6000
mmlu_high_school_biology	0.9484
mmlu_high_school_chemistry	0.8571
mmlu_high_school_computer_science	0.9400
mmlu_high_school_european_history	0.8788
mmlu_high_school_geography	0.9394
mmlu_high_school_government_and_politics	0.9845
mmlu_high_school_macroeconomics	0.9231
mmlu_high_school_mathematics	0.6037
mmlu_high_school_microeconomics	0.9664
mmlu_high_school_physics	0.8146
mmlu_high_school_psychology	0.9505
mmlu_high_school_statistics	0.8704
mmlu_high_school_us_history	0.9510
mmlu_high_school_world_history	0.9030
mmlu_human_aging	0.8386
mmlu_human_sexuality	0.9084
mmlu_humanities	0.7798
mmlu_international_law	0.9339
mmlu_jurisprudence	0.9074
mmlu_logical_fallacies	0.9080
mmlu_machine_learning	0.7946
mmlu_management	0.9320
mmlu_marketing	0.9573
mmlu_medical_genetics	0.9300
mmlu_miscellaneous	0.9259
mmlu_moral_disputes	0.8266
mmlu_moral_scenarios	0.6927
mmlu_nutrition	0.8987
mmlu_other	0.8610
mmlu_philosophy	0.8489
mmlu_prehistory	0.8827
mmlu_professional_accounting	0.7482
mmlu_professional_law	0.6923
mmlu_professional_medicine	0.9191
mmlu_professional_psychology	0.8742
mmlu_public_relations	0.7636
mmlu_security_studies	0.8204
mmlu_social_sciences	0.9058
mmlu_sociology	0.9303
mmlu_stem	0.8411
mmlu_us_foreign_policy	0.9400
mmlu_virology	0.5723
mmlu_world_religions	0.8830
piqa	0.7873

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 = "Qwen3.5-27B-Writer-V2-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

bash

vllm serve Qwen3.5-27B-Writer-V2-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.

LeaderboardModel1/Qwen3.5-27B-Writer-V2-AutoRound-MXFP4-RTN

Qwen3.5-27B-Writer-V2-AutoRound-MXFP4-RTN

Model Details