Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Latency Measurement on LLaMA linear layers (11008 × 4096) 7B
Loading...
0.0512
Latency (ms)
MBOK
-0.07321
0.766355
1.60592
2.445485
May 28, 2025
Latency (ms)
Speed-up
Updated 1mo ago
Evaluation Results
Method
Method
Links
Latency (ms)
Speed-up
MBOK
WEIGHT SIZE=11008 × 40...
2025.05
0.0512
5.41
FP16
WEIGHT SIZE=11008 × 40...
2025.05
0.2766
-
QUIP#
WEIGHT SIZE=11008 × 40...
2025.05
0.5599
0.49
QTIP
WEIGHT SIZE=11008 × 40...
2025.05
3.1607
0.09
Feedback
Search any
task
Search any
task