DetectFPS
Submit a build

Intel NPU (Core Ultra)

AcceleratorOpenVINO (Intel)

6 builds on DetectFPS: 6 Frigate docs references and 0 community builds. All 6 are usable for stats. Hardware id intel-npu.

Estimate capacityCompare Submit a build with this device
Median inference
22 ms
all models · 6 usable builds
Fastest model
6 ms
mobilenet-v2 · 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
mobilenet-v2
6 ms
1 docs reference
167 det/s
39
yolov9-s · 320
11 ms
1 docs reference
91 det/s
21
yolo-nas · 320
14 ms
1 docs reference
71 det/s
17
yolov9-s · 640
30 ms
1 docs reference
33 det/s
8
yolo-nas · 640
34 ms
1 docs reference
29 det/s
7
rf-detr-nano · 320
40 ms
1 docs reference
25 det/s
6

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-039 Frigate docs mobilenetv2 6 ms — — checked 2026-10-19
db-040 Frigate docs yolov9-s 320 11 ms — — checked 2026-10-19
db-042 Frigate docs yolo-nas 320 14 ms — — checked 2026-10-19
db-041 Frigate docs yolov9-s 640 30 ms — — checked 2026-10-19
db-043 Frigate docs yolo-nas 640 34 ms — — checked 2026-10-19
db-044 Frigate docs rf-detr nano 320 40 ms — — checked 2026-10-19

Community builds first, then docs references.