List your company

LLM Evaluation on Qwen3-1.7B Evaluation Suite (avg)

58.64Average PerformanceBF16
27.970435.932743.89551.8573Apr 10, 2026

Evaluation results

MethodLinks
BF16Quantization Bit-width (W-A-KV)=W16-A16-KV162026.0458.64
EDGERAZORQuantization Bit-width (W-A-KV)=W4-A16-KV162026.0458.56
AutoRoundQuantization Bit-width (W-A-KV)=W4-A16-KV162026.0458.31
AQLMQuantization Bit-width (W-A-KV)=W4-A16-KV162026.0457.57
GPTAQQuantization Bit-width (W-A-KV)=W4-A16-KV162026.0457.05
AWQQuantization Bit-width (W-A-KV)=W4-A16-KV162026.0456.95
VPTQQuantization Bit-width (W-A-KV)=W4-A16-KV162026.0456.52
GPTQQuantization Bit-width (W-A-KV)=W4-A16-KV162026.0454.94
EDGERAZORQuantization Bit-width (W-A-KV)=W3-A16-KV162026.0453.33
AutoRoundQuantization Bit-width (W-A-KV)=W3-A16-KV162026.0451.48
AQLMQuantization Bit-width (W-A-KV)=W3-A16-KV162026.0451.24
Q-PaletteQuantization Bit-width (W-A-KV)=W4-A16-KV162026.0449.77
AWQQuantization Bit-width (W-A-KV)=W3-A16-KV162026.0447.71
Q-PaletteQuantization Bit-width (W-A-KV)=W3-A16-KV162026.0447.66
VPTQQuantization Bit-width (W-A-KV)=W3-A16-KV162026.0447.44
EDGERAZORQuantization Bit-width (W-A-KV)=W2-A16-KV162026.0447.14
Slim-LLM+Quantization Bit-width (W-A-KV)=W3-A16-KV162026.0446.8
QTIPQuantization Bit-width (W-A-KV)=W2-A16-KV162026.0445.85
OmniQuantQuantization Bit-width (W-A-KV)=W4-A16-KV162026.0444.76
GPTAQQuantization Bit-width (W-A-KV)=W3-A16-KV162026.0444.45
EDGERAZORQuantization Bit-width (W-A-KV)=W1.58-A16-KV162026.0443.89
GPTQQuantization Bit-width (W-A-KV)=W3-A16-KV162026.0443.14
AQLMQuantization Bit-width (W-A-KV)=W2-A16-KV162026.0441.44
OmniQuantQuantization Bit-width (W-A-KV)=W3-A16-KV162026.0440.65
AutoRoundQuantization Bit-width (W-A-KV)=W2-A16-KV162026.0435.27
VPTQQuantization Bit-width (W-A-KV)=W2-A16-KV162026.0433.13
Q-PaletteQuantization Bit-width (W-A-KV)=W2-A16-KV162026.0433.06
QuIP#Quantization Bit-width (W-A-KV)=W3-A16-KV162026.0432.88
QuIP#Quantization Bit-width (W-A-KV)=W4-A16-KV162026.0432.67
OmniQuantQuantization Bit-width (W-A-KV)=W2-A16-KV162026.0432.62
Slim-LLM+Quantization Bit-width (W-A-KV)=W2-A16-KV162026.0432.26
QuIP#Quantization Bit-width (W-A-KV)=W2-A16-KV162026.0431.33
Q-PaletteQuantization Bit-width (W-A-KV)=W1.58-A16-KV162026.0430.92
AWQQuantization Bit-width (W-A-KV)=W2-A16-KV162026.0430.85
ARB-LLMQuantization Bit-width (W-A-KV)=W1.58-A16-KV162026.0430.61
GPTAQQuantization Bit-width (W-A-KV)=W2-A16-KV162026.0429.98
GPTQQuantization Bit-width (W-A-KV)=W2-A16-KV162026.0429.82
BiLLMQuantization Bit-width (W-A-KV)=W1.58-A16-KV162026.0429.15