Nvidia RTX 3070
AcceleratorONNX (Nvidia / GPU)
6 builds on DetectFPS: 6 Frigate docs references and 0 community builds. All 6 are usable for stats. Hardware id nvidia-rtx-3070.
Median inference
8.5 ms
all models · 6 usable builds
Fastest model
6 ms
yolov9-t · 320 · 1 docs reference
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
yolov9-t · 320
6 ms
1 docs reference
167 det/s
39
yolo-nas · 320
8 ms
1 docs reference
125 det/s
30
yolov9-s · 320
8 ms
1 docs reference
125 det/s
30
rf-detr-nano · 320
9 ms
1 docs reference
111 det/s
26
yolo-nas · 640
14 ms
1 docs reference
71 det/s
17
yolov9-s · 640
25 ms
1 docs reference
40 det/s
9
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.