Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Inference Efficiency on Edge Device
Loading...
43.36
Latency (s)
RAP
41.7556
52.5853
63.415
74.2447
May 22, 2025
Latency (s)
Throughput (token/s)
Updated 15d ago
Evaluation Results
Method
Method
Links
Latency (s)
Throughput (token/s)
RAP
2025.05
43.36
47.23
DENSE
2025.05
52.4
39.08
SLICEGPT
2025.05
64.64
31.68
LLM-PRUNER
2025.05
83.47
24.53
Feedback
Search any
task
Search any
task