Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Large Language Model Evaluation on LLaMA 1B 3.2
Loading...
9.75
Perplexity (PPL)
baseline
-6,109.86
35,197.5075
76,504.875
117,812.2425
Mar 9, 2026
Perplexity (PPL)
Zero-Shot Performance
MMLU Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Perplexity (PPL)
Zero-Shot Performance
MMLU Score
baseline
#Bits=FP16
2026.03
9.75
54.82
36.76
SERQ
#Bits=W4A4
2026.03
12.52
50.44
26.34
QuaRot
#Bits=W4A4
2026.03
13.17
50.03
26.64
SpinQuant
#Bits=W4A4
2026.03
13.47
48.95
26.38
SmoothQ(g128)
#Bits=W4A4
2026.03
69.22
40.04
24.43
SmoothQ
#Bits=W4A4
2026.03
153,000
35.59
24.37
Feedback
Search any
task
Search any
task
