Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Latency Measurement on LLaMA-7B linear layers (4096 × 4096)
Loading...
0.0499
Latency (ms)
MBOK
-0.002969
0.35383
0.71063
1.06743
May 28, 2025
Latency (ms)
Speed-up
Updated 1mo ago
Evaluation Results
Method
Method
Links
Latency (ms)
Speed-up
MBOK
WEIGHT SIZE=4096 × 409...
2025.05
0.0499
2.14
FP16
WEIGHT SIZE=4096 × 409...
2025.05
0.107
-
QUIP#
WEIGHT SIZE=4096 × 409...
2025.05
0.462
0.23
QTIP
WEIGHT SIZE=4096 × 409...
2025.05
1.3714
0.08
Feedback
Search any
task
Search any
task
