Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Large Language Model Evaluation on LLaMA-3 8B
Loading...
6.13
PPL
baseline
-18,833.6248
108,334.7201
235,503.065
362,671.4099
Mar 9, 2026
PPL
Zero-Shot Score
MMLU Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
PPL
Zero-Shot Score
MMLU Score
baseline
#Bits=FP16
2026.03
6.13
67.16
62.13
SERQ
#Bits=W4A4
2026.03
7.75
62.41
53.8
SpinQuant
#Bits=W4A4
2026.03
8.26
61.75
49.93
QuaRot
#Bits=W4A4
2026.03
8.41
59.12
47.29
SmoothQ(g128)
#Bits=W4A4
2026.03
17.26
48.97
29.3
SmoothQ
#Bits=W4A4
2026.03
471,000
36.34
25.17
Feedback
Search any
task
Search any
task