Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multimodal Understanding Inference Efficiency on InternVL2.5-8B
Loading...
56.89
Reduction Ratio
LUVC
-2.2756
13.0847
28.445
43.8053
Dec 9, 2025
Reduction Ratio
Throughput Ratio
GPU Memory (GB)
Updated 4d ago
Evaluation Results
Method
Method
Links
Reduction Ratio
Throughput Ratio
GPU Memory (GB)
LUVC
reduction_strategy=Lin...
2025.12
56.89
214
18.68
PACT
reduction_strategy=PACT
2025.12
42
155
19.68
VTW
reduction_strategy=Vis...
2025.12
40.25
140
19.54
No reduction
reduction_strategy=None
2025.12
0
100
21.79
Feedback
Search any
task
Search any
task