DetectFPS
Submit a build

Nvidia RTX 3050

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-3050.

Estimate capacityCompare Submit a build with this device
Median inference
11 ms
all models · 6 usable builds
Fastest model
8 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 estimates
Model · inputMedianCapacityCameras
yolov9-t · 320
8 ms
1 docs reference
125 det/s
30
yolo-nas · 320
10 ms
1 docs reference
100 det/s
24
yolov9-s · 320
10 ms
1 docs reference
100 det/s
24
rf-detr-nano · 320
12 ms
1 docs reference
83 det/s
19
yolo-nas · 640
16 ms
1 docs reference
63 det/s
15
yolov9-s · 640
28 ms
1 docs reference
36 det/s
8

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
db-061 Frigate docs yolov9-t 320 8 ms — — checked 2026-10-19
db-062 Frigate docs yolov9-s 320 10 ms — — checked 2026-10-19
db-065 Frigate docs yolo-nas 320 10 ms — — checked 2026-10-19
db-064 Frigate docs rf-detr nano 320 12 ms — — checked 2026-10-19
db-066 Frigate docs yolo-nas 640 16 ms — — checked 2026-10-19
db-063 Frigate docs yolov9-s 640 28 ms — — checked 2026-10-19

Community builds first, then docs references.