Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Inference Latency on VLM prefill 512 tokens
Loading...
59.4
Prefill Latency (ms)
W4A8
59.024
61.562
64.1
66.638
Dec 27, 2024
Prefill Latency (ms)
Updated 4d ago
Evaluation Results
Method
Method
Links
Prefill Latency (ms)
W4A8
Model=LLaVA-onevision-...
2024.12
59.4
FP16
Model=LLaVA-onevision-...
2024.12
68.8
Feedback
Search any
task
Search any
task