Nvidia RTX 3060
AcceleratorONNX (Nvidia / GPU)TensorRT (Nvidia, legacy)
4 builds on DetectFPS: 0 Frigate docs references and 4 community builds. 3 usable for stats. Hardware id nvidia-rtx-3060.
Median inference
10 ms
all models · 3 usable builds
Fastest model
6 ms
yolov7 · 320 · 1 community build
Most cameras seen
—
no camera counts reported
Price
not tracked
no verified price yet
Max detectors
—
no limit recorded
Median inference by model
Capacity and cameras are estimatesModel · inputMedianCapacityCameras
yolov7 · 320
6 ms
1 community build
167 det/s
39
yolov7
10 ms
1 community build
100 det/s
24
yolov9-t
12 ms
1 community build
83 det/s
19
Bars show relative throughput (fastest model = full). Capacity = 1000 ÷ median ms for one detector. Cameras = how many at 5 fps and Typical activity stay under 60% of that capacity. Where a row mixes docs and community numbers, treat the median as a range rather than a point.
All builds for this device
Open in the database →BuildSourceModelSpeedCamsFrigatePosted
Community builds first, then docs references. db-139: “(low GPU utilization issue)” db-140: “TensorRT execution provider. Improved from 28-34 ms (default ONNX) to 10-14 ms.” db-141: “avg 10 ms (40 ms with onnx)”