Google Coral M.2 / PCIe (single Edge TPU)

AcceleratorCoral (EdgeTPU)

2 builds on DetectFPS: 0 Frigate docs references and 2 community builds. All 2 are usable for stats. Hardware id coral-m2-pcie.

Median inference
13 ms
all models · 2 usable builds
Fastest model
7 ms
frigate-default · 1 community build
Most cameras seen
4
db-125 · edgetpu_model.tflite 320
Price
not tracked
no verified price yet
Max detectors
—
no limit recorded

Median inference by model

Capacity and cameras are estimates
Model · inputMedianCapacityCameras
frigate-default
7 ms
1 community build
143 det/s
34
frigate-default · 320
19 ms
1 community build
53 det/s
12

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-123 community default 7 ms — — Sep 2023 · GitHub #7601
db-125 community edgetpu_model.tflite 320 19 ms 4 — Sep 2023 · GitHub #7601

Community builds first, then docs references. db-123: “Same post: ~25 ms on USB Coral”