Share your thoughts, 1 month free Claude Pro on usSee more

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

47.83Average Performance

EDGERAZOR

Updated 2mo ago

Evaluation Results

Method	Links
EDGERAZOR 2026.04		47.83
BF16 2026.04		47.35
AQLM 2026.04		46.48
AutoRound 2026.04		45.75
AWQ 2026.04		44.65
GPTAQ 2026.04		44.49
EDGERAZOR 2026.04		44.17
GPTQ 2026.04		43.71
VPTQ 2026.04		41.69
EDGERAZOR 2026.04		41.6
Q-Palette 2026.04		40.97
AutoRound 2026.04		40.96
AQLM 2026.04		39.85
EDGERAZOR 2026.04		39.77
Q-Palette 2026.04		37.55
VPTQ 2026.04		37.46
OmniQuant 2026.04		36.6
AQLM 2026.04		36.51
QTIP 2026.04		35.94
GPTAQ 2026.04		35.61
QuIP# 2026.04		35.42
AWQ 2026.04		35.37
OmniQuant 2026.04		34.57
GPTQ 2026.04		34.53
Slim-LLM+ 2026.04		33.95
AutoRound 2026.04		31.8
VPTQ 2026.04		31.42
AWQ 2026.04		31.02
Q-Palette 2026.04		30.81
ARB-LLM 2026.04		30.77
OmniQuant 2026.04		30.7
Q-Palette 2026.04		30.66
Slim-LLM+ 2026.04		30.54
QuIP# 2026.04		30.07
GPTQ 2026.04		30
BiLLM 2026.04		29.98
QuIP# 2026.04		29.9
GPTAQ 2026.04		29.8