Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
INT2 Quantization on OPT-125M
Loading...
1.39
Memory Cost (GB)
OPTQ
1.3068
1.8684
2.43
2.9916
Feb 14, 2024
Memory Cost (GB)
Updated 4d ago
Evaluation Results
Method
Method
Links
Memory Cost (GB)
OPTQ
Target=layer-wise reco...
2024.02
1.39
Z-FOLD
Target=layer-wise reco...
2024.02
1.39
OPTQ
Target=layer-wise reco...
2024.02
1.39
Z-FOLD
Target=layer-wise reco...
2024.02
1.39
aespa
Target=attention-wise...
2024.02
1.68
aespa
Target=attention-wise...
2024.02
1.68
OmniQuant
Target=attention-wise...
2024.02
1.94
OmniQuant
Target=attention-wise...
2024.02
1.94
BRECQ
Target=attention-wise...
2024.02
3.39
BRECQ
Target=attention-wise...
2024.02
3.39
AffineQuant
Target=attention-wise...
2024.02
3.47
AffineQuant
Target=attention-wise...
2024.02
3.47
Feedback
Search any
task
Search any
task