Nvidia RTX 3060
ONNX (Nvidia / GPU) · (low GPU utilization issue)
Speed28–29 ms
Cameras—
Modelrf-detr
Version0.16
- AcceleratorNvidia RTX 3060price not tracked
- Host—
- CPU—
Aug 25, 2025GitHub #19741
Nvidia RTX 3060 · yolov7 trt
Frigate 0.16.0-beta3-tensorrtCommunity build
I run this too, add my numbers
Opens the submit form prefilled with this hardware, model and version
Inference
10 ms
as reported
Est. capacity
~100 det/s
1000 ÷ 10 ms · estimate
Cameras
—
not reported
CPU
—
not reported
Power
—
not reported
Parts
prices show only once verified by handAccelerator
Nvidia RTX 3060
ONNX (Nvidia / GPU), TensorRT (Nvidia, legacy) · 4 builds on DetectFPS
price not tracked yet
Get price drops in the weekly newsletter
Host
—
not reported
—
CPU
AMD Ryzen 5 3600
as reported
—
Cameras
—
resolution not reported
—
Tracked totalno verified prices yet
Setup
Detector
TensorRT (Nvidia, legacy)
Detector instances
—
Model, as reported
yolov7 trt
Model family · input
yolov7 · input not stated
Camera resolution
—
Cameras
—
Frigate version
0.16.0-beta3-tensorrt (0.16 series, 2 behind newest)
OS
—
Numbers
dashes mean the source didn't sayInference
10 ms
Inference range
—
Total fps
—
CPU
—
Power
—
Used in stats
Yes
Notes and flags
avg 10 ms (40 ms with onnx)
Source
Where
Date, as the source wrote it
2025-08 (month precision)
Added to DetectFPS
from a public post; numbers copied as written, not re-tested
Similar builds
Same device, then the same model family
Nvidia RTX 3060
TensorRT (Nvidia, legacy)
older version, may be outdated
Speed5–7 ms
Cameras—
Modelyolov7-320
Version0.15.2
- AcceleratorNvidia RTX 3060price not tracked
- Host—
- CPU—
Aug 2025GitHub #19741
Nvidia RTX 3060
ONNX (Nvidia / GPU)
Speed10–14 ms
Cameras—
Modelyolov9-t
Version0.16
- AcceleratorNvidia RTX 3060price not tracked
- Host—
- CPU—
Aug 2025GitHub #19741
3 other builds use the same device.