Models
Per-model version, accuracy, GPU utilization, latency, and deploy status.
Inference latency by model
GPU utilization by model
7 models
| Model / Status | Type | Version | Nodes | GPU | Latency | Accuracy | Updated |
|---|
yolo-maritime Deployed | Object Detector | v3.3 | 840/840 | 34% | 12 ms | 91.4% | 2 days ago | Deploy | |
grounding-dino Deployed | Grounded Detector | v1.8 | 210/840 | 72% | 85 ms | 88.2% | 1 week ago | Deploy | |
florence-vlm Deploying | Vision-Language | v0.9 | 42/840 | 91% | 240 ms | 82.7% | In progress | Deploy | |
track-maritime Deployed | Multi-Object Tracker | v2.1 | 840/840 | 18% | 8 ms | 94.1% | 5 days ago | Deploy | |
anomaly-detect Degraded | Anomaly Detector | v1.0 | 180/840 | 45% | 32 ms | 76.3% | 3 weeks ago | Deploy |
1–5 of 7 models