Intel HD / UHD 630 (7th-9th gen iGPU)
AcceleratorOpenVINO (Intel)
7 builds on DetectFPS: 2 Frigate docs references and 5 community builds. All 7 are usable for stats. Hardware id intel-uhd-630.
Median inference
21 ms
all models · 7 usable builds
Fastest model
13 ms
yolov8n · 288 · 1 community build
Most cameras seen
8
db-171 · yolov9
Price
not tracked
no verified price yet
Max detectors
—
no limit recorded
Median inference by model
Capacity and cameras are estimatesModel · inputMedianCapacityCameras
yolov8n · 288
13 ms
1 community build
77 det/s
18
mobilenet-v2
15 ms
1 docs reference
67 det/s
16
yolov8s · 288
18 ms
1 community build
56 det/s
13
yolov9-t
21 ms
1 community build
48 det/s
11
yolov9
26 ms
1 community build
38 det/s
9
yolo-nas · 320
30 ms
1 docs reference
33 det/s
8
yolov8m · 288
42 ms
1 community build
24 det/s
5
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-171: “Single detector; detector CPU up to 100%. Two detectors ran 30+ ms each.”