Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
INT2 Quantization on LLaMA-13B
Loading...
12.34
Memory Cost (GB)
OPTQ
11.6628
16.2339
20.805
25.3761
Feb 14, 2024
Memory Cost (GB)
Updated 4d ago
Evaluation Results
Method
Method
Links
Memory Cost (GB)
OPTQ
Target=layer-wise reco...
2024.02
12.34
Z-FOLD
Target=layer-wise reco...
2024.02
12.34
OPTQ
Target=layer-wise reco...
2024.02
12.34
Z-FOLD
Target=layer-wise reco...
2024.02
12.34
OmniQuant
Target=attention-wise...
2024.02
17.02
OmniQuant
Target=attention-wise...
2024.02
17.02
AffineQuant
Target=attention-wise...
2024.02
27.1
AffineQuant
Target=attention-wise...
2024.02
27.1
aespa
Target=attention-wise...
2024.02
29.27
aespa
Target=attention-wise...
2024.02
29.27
Feedback
Search any
task
Search any
task