List your company
ResearchFormerly WizWand

Large Language Model Evaluation on Qwen3-0.6B (test)

47.83Average PerformanceEDGERAZOR
29.078833.946938.81543.6831Apr 10, 2026
Updated 6mo ago

Evaluation results

MethodLinks
EDGERAZORQuantization Configuration=W4-A16-KV16, Weight bit-width=4, Activation bit-width=16, KV cache bit-width=162026.0447.83
BF16Quantization Configuration=W16-A16-KV16, Weight bit-width=16, Activation bit-width=16, KV cache bit-width=162026.0447.35
AQLMQuantization Configuration=W4-A16-KV16, Weight bit-width=4, Activation bit-width=16, KV cache bit-width=162026.0446.48
AutoRoundQuantization Configuration=W4-A16-KV16, Weight bit-width=4, Activation bit-width=16, KV cache bit-width=162026.0445.75
AWQQuantization Configuration=W4-A16-KV16, Weight bit-width=4, Activation bit-width=16, KV cache bit-width=162026.0444.65
GPTAQQuantization Configuration=W4-A16-KV16, Weight bit-width=4, Activation bit-width=16, KV cache bit-width=162026.0444.49
EDGERAZORQuantization Configuration=W2.79-A16-KV16, Weight bit-width=2.79, Activation bit-width=16, KV cache bit-width=162026.0444.17
GPTQQuantization Configuration=W4-A16-KV16, Weight bit-width=4, Activation bit-width=16, KV cache bit-width=162026.0443.71
VPTQQuantization Configuration=W4-A16-KV16, Weight bit-width=4, Activation bit-width=16, KV cache bit-width=162026.0441.69
EDGERAZORQuantization Configuration=W1.88-A16-KV16, Weight bit-width=1.88, Activation bit-width=16, KV cache bit-width=162026.0441.6
Q-PaletteQuantization Configuration=W4-A16-KV16, Weight bit-width=4, Activation bit-width=16, KV cache bit-width=162026.0440.97
AutoRoundQuantization Configuration=W3-A16-KV16, Weight bit-width=3, Activation bit-width=16, KV cache bit-width=162026.0440.96
AQLMQuantization Configuration=W3-A16-KV16, Weight bit-width=3, Activation bit-width=16, KV cache bit-width=162026.0439.85
EDGERAZORQuantization Configuration=W1.58-A16-KV16, Weight bit-width=1.58, Activation bit-width=16, KV cache bit-width=162026.0439.77
Q-PaletteQuantization Configuration=W3.25-A16-KV16, Weight bit-width=3.25, Activation bit-width=16, KV cache bit-width=162026.0437.55
VPTQQuantization Configuration=W3-A16-KV16, Weight bit-width=3, Activation bit-width=16, KV cache bit-width=162026.0437.46
OmniQuantQuantization Configuration=W4-A16-KV16, Weight bit-width=4, Activation bit-width=16, KV cache bit-width=162026.0436.6
AQLMQuantization Configuration=W2-A16-KV16, Weight bit-width=2, Activation bit-width=16, KV cache bit-width=162026.0436.51
QTIPQuantization Configuration=W2-A16-KV16, Weight bit-width=2, Activation bit-width=16, KV cache bit-width=162026.0435.94
GPTAQQuantization Configuration=W3-A16-KV16, Weight bit-width=3, Activation bit-width=16, KV cache bit-width=162026.0435.61
QuIP#Quantization Configuration=W3-A16-KV16, Weight bit-width=3, Activation bit-width=16, KV cache bit-width=162026.0435.42
AWQQuantization Configuration=W3-A16-KV16, Weight bit-width=3, Activation bit-width=16, KV cache bit-width=162026.0435.37
OmniQuantQuantization Configuration=W3-A16-KV16, Weight bit-width=3, Activation bit-width=16, KV cache bit-width=162026.0434.57
GPTQQuantization Configuration=W3-A16-KV16, Weight bit-width=3, Activation bit-width=16, KV cache bit-width=162026.0434.53
Slim-LLM+Quantization Configuration=W3-A16-KV16, Weight bit-width=3, Activation bit-width=16, KV cache bit-width=162026.0433.95
AutoRoundQuantization Configuration=W2-A16-KV16, Weight bit-width=2, Activation bit-width=16, KV cache bit-width=162026.0431.8
VPTQQuantization Configuration=W2-A16-KV16, Weight bit-width=2, Activation bit-width=16, KV cache bit-width=162026.0431.42
AWQQuantization Configuration=W2-A16-KV16, Weight bit-width=2, Activation bit-width=16, KV cache bit-width=162026.0431.02
Q-PaletteQuantization Configuration=W1.75-A16-KV16, Weight bit-width=1.75, Activation bit-width=16, KV cache bit-width=162026.0430.81
ARB-LLMQuantization Configuration=W1.00-A16-KV16, Weight bit-width=1.00, Activation bit-width=16, KV cache bit-width=162026.0430.77
OmniQuantQuantization Configuration=W2-A16-KV16, Weight bit-width=2, Activation bit-width=16, KV cache bit-width=162026.0430.7
Q-PaletteQuantization Configuration=W2-A16-KV16, Weight bit-width=2, Activation bit-width=16, KV cache bit-width=162026.0430.66
Slim-LLM+Quantization Configuration=W2-A16-KV16, Weight bit-width=2, Activation bit-width=16, KV cache bit-width=162026.0430.54
QuIP#Quantization Configuration=W2-A16-KV16, Weight bit-width=2, Activation bit-width=16, KV cache bit-width=162026.0430.07
GPTQQuantization Configuration=W2-A16-KV16, Weight bit-width=2, Activation bit-width=16, KV cache bit-width=162026.0430
BiLLMQuantization Configuration=W1.06-A16-KV16, Weight bit-width=1.06, Activation bit-width=16, KV cache bit-width=162026.0429.98
QuIP#Quantization Configuration=W4-A16-KV16, Weight bit-width=4, Activation bit-width=16, KV cache bit-width=162026.0429.9
GPTAQQuantization Configuration=W2-A16-KV16, Weight bit-width=2, Activation bit-width=16, KV cache bit-width=162026.0429.8