Model Details This model is mxfp4 quantized version of Qwen/Qwen3 30B A3B Instruct 2507 based on intel/auto round saved with llm compressor format. Please follow the license of the original model. Eval Results Eval with vllm==0.25.1 Precision hellaswag piqa mmlu gsm8k average bf16 0.6119 0.8052 0.8026 0.9371 0.78920 mxfp4 RTN 0.5995 0.7927 0.7910 0.9303 0.77838 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: Intel Neural Compressor AutoRound 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 consul…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy