Nvidia RTX 5070 Ti

AcceleratorONNX (Nvidia / GPU)

1 build on DetectFPS: 0 Frigate docs references and 1 community build. All 1 are usable for stats. Hardware id nvidia-rtx-5070-ti.

Median inference
10.5 ms
all models · 1 usable build
Fastest model
10.5 ms
yolov9-s · 320 · 1 community build
Most cameras seen
20
db-155 · yolov9-s 320
Price
not tracked
no verified price yet
Max detectors
—
no limit recorded

Median inference by model

Capacity and cameras are estimates
Model · inputMedianCapacityCameras
yolov9-s · 320
10.5 ms
1 community build
95 det/s
22

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-155 yolov9-s 320 10.5 ms 20 0.17.2 Aug 13, 2026 · GitHub #23978

Community builds first, then docs references. db-155: “About 20-25 cameras (20 recorded).”