Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Resource Utilization on MSR-VTT (Video-Language Understanding)
Loading...
3,751
Initial Memory (MB)
Video-LLaMA3
2,776.88
9,352.19
15,927.5
22,502.81
Apr 9, 2026
Initial Memory (MB)
Peak Memory (MB)
Memory Increase (MB)
Throughput (tokens/s)
Updated 9d ago
Evaluation Results
Method
Method
Links
Initial Memory (MB)
Peak Memory (MB)
Memory Increase (MB)
Throughput (tokens/s)
Video-LLaMA3
Size=2B
2026.04
3,751
26,705
22,955
33.5
InternVL2.5
Size=2.2B
2026.04
4,593
12,698
8,105
31.5
ABMamba
Size=3.6B
2026.04
7,088
7,570
482
95.4
Video-ChatGPT
Size=7B
2026.04
13,440
15,505
2,066
38.1
LLaVA-OneVision
Size=7B
2026.04
15,813
21,004
5,191
24.8
Video-LLaVA
Size=7B
2026.04
28,104
30,652
2,548
28.9
Feedback
Search any
task
Search any
task