Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multimodal Inference Latency on ScienceQA IMG
Loading...
919.25
Throughput (token/s)
MobileVLM-1.7B
-16.9476
226.1037
469.155
712.2063
May 15, 2024
Throughput (token/s)
Total Latency (s)
Updated 3d ago
Evaluation Results
Method
Method
Links
Throughput (token/s)
Total Latency (s)
MobileVLM-1.7B
Model Size=1.7B
2024.05
919.25
579.88
Xmodel-VLM
Model Size=1.1B
2024.05
415.69
1,360.25
LLaVA-7B
Model Size=7B
2024.05
19.06
1,090.32
Feedback
Search any
task
Search any
task