Qwen3-0.6B-AutoRound-MXFP4-RTN

Model Details

This model is a MXFP4 (Microscaling FP4) quantization of Qwen/Qwen3-0.6B generated by AutoRound. Please follow the license of the original model.

Quantization Details

Attribute	Value
Base Model	Qwen/Qwen3-0.6B
Quantization Tool	AutoRound
Quantization Scheme	MXFP4
Quantized Size	767 MB

Evaluation Results

Task	Accuracy
hellaswag	0.3454
mmlu	0.3426
mmlu_abstract_algebra	0.2700
mmlu_anatomy	0.3333
mmlu_astronomy	0.3289
mmlu_business_ethics	0.3600
mmlu_clinical_knowledge	0.3547
mmlu_college_biology	0.3264
mmlu_college_chemistry	0.3400
mmlu_college_computer_science	0.3100
mmlu_college_mathematics	0.3100
mmlu_college_medicine	0.3699
mmlu_college_physics	0.2745
mmlu_computer_security	0.4200
mmlu_conceptual_physics	0.3106
mmlu_econometrics	0.2281
mmlu_electrical_engineering	0.4069
mmlu_elementary_mathematics	0.2646
mmlu_formal_logic	0.3016
mmlu_global_facts	0.2000
mmlu_high_school_biology	0.3710
mmlu_high_school_chemistry	0.3153
mmlu_high_school_computer_science	0.3600
mmlu_high_school_european_history	0.3879
mmlu_high_school_geography	0.3990
mmlu_high_school_government_and_politics	0.4508
mmlu_high_school_macroeconomics	0.3333
mmlu_high_school_mathematics	0.2778
mmlu_high_school_microeconomics	0.3319
mmlu_high_school_physics	0.2781
mmlu_high_school_psychology	0.4422
mmlu_high_school_statistics	0.2824
mmlu_high_school_us_history	0.3922
mmlu_high_school_world_history	0.4473
mmlu_human_aging	0.3677
mmlu_human_sexuality	0.3893
mmlu_humanities	0.3143
mmlu_international_law	0.3967
mmlu_jurisprudence	0.3889
mmlu_logical_fallacies	0.4294
mmlu_machine_learning	0.2054
mmlu_management	0.4466
mmlu_marketing	0.4573
mmlu_medical_genetics	0.4000
mmlu_miscellaneous	0.3640
mmlu_moral_disputes	0.3150
mmlu_moral_scenarios	0.2547
mmlu_nutrition	0.3889
mmlu_other	0.3624
mmlu_philosophy	0.3441
mmlu_prehistory	0.3148
mmlu_professional_accounting	0.2766
mmlu_professional_law	0.2757
mmlu_professional_medicine	0.3272
mmlu_professional_psychology	0.3856
mmlu_public_relations	0.3000
mmlu_security_studies	0.4531
mmlu_social_sciences	0.3975
mmlu_sociology	0.4776
mmlu_stem	0.3118
mmlu_us_foreign_policy	0.5400
mmlu_virology	0.3976
mmlu_world_religions	0.3626
piqa	0.6235

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 = "Qwen3-0.6B-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 Qwen3-0.6B-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.