Hailo-8L (M.2) · yolov9-tiny 320

Frigate docs reference

Checked 2026-10-19· Frigate docs hardware page ·db-005

I run this too, add my numbers Opens the submit form prefilled with this hardware, model and version

Inference

18 ms

docs reference

Est. capacity

~56 det/s

1000 ÷ 18 ms · estimate

Cameras

—

not reported

CPU

—

not reported

Power

—

not reported

Parts

prices show only once verified by hand

Accelerator

Hailo-8L (M.2)

Hailo · 3 builds on DetectFPS · reported as “Hailo-8L”

price not tracked yet

View at up-shop.org

Get price drops in the weekly newsletter

Price drops, once a week

When a tracked price is verified or drops, it goes in the newsletter alongside new benchmarks. No per-device alerts and no tracking: the newsletter is the only list.

Newsletter coming soon The signup form appears here as soon as the newsletter embed code is pasted into site.json. Issue #1 is already readable here.

Host

—

not reported

—

CPU

—

not reported

—

Cameras

—

resolution not reported

—

Tracked totalno verified prices yet

Setup

Detector

Hailo

Detector instances

—

Model, as reported

yolov9-tiny 320

Model family · input

yolov9-t · 320

Camera resolution

—

Cameras

—

Frigate version

—

Numbers

dashes mean the source didn't say

Inference

18 ms

Inference range

—

Total fps

—

CPU

—

Power

—

Used in stats

Yes

Source

Where

docs.frigate.video/frigate/hardware

Date, as the source wrote it

—

Added to DetectFPS

copied from the Frigate project's hardware page on 2026-10-19; approximate reference value

What this build implies

~56 detections per second

1000 ÷ 18 ms. No camera count was reported, so use the calculator to see what that covers: at 5 fps and Typical activity, that is about 13 cameras comfortably.

Open in the calculator

Hardware

Hailo-8L (M.2)

Detector type

Hailo

Builds on DetectFPS

Median, this model

18 ms (1 build)

Price

price not tracked yet

Shown because this guide lists Hailo-8L (M.2) in its hardware (hardware_ids). Cross-device guides are only linked when they name this device or its host.

Hailo-8L vs Google Coral for Frigate (2026): Speeds, Prices, Which to Buy →

Shown because this guide lists Hailo-8L (M.2) in its hardware (hardware_ids). Cross-device guides are only linked when they name this device or its host.

Raspberry Pi 5 + Hailo AI HAT for Frigate: Does It Work? →

Shown because this guide lists Hailo-8L (M.2) in its hardware (hardware_ids). Cross-device guides are only linked when they name this device or its host.

Affiliate links

DetectFPS may earn a commission when you buy through links on this site. It never changes which builds we show or how they rank. Buy buttons say “affiliate link” whenever one is used; none is used on this page.

Similar builds

Same device, then the same model family

Hailo-8L (M.2)

Hailo

Frigate docs

Speed10 ms

Cameras—

Modelssd mobilenet v1

Version—

AcceleratorHailo-8L (M.2)price not tracked
Host—
CPU—

checked 2026-10-19Frigate docs

Hailo-8L (M.2)

Hailo

Frigate docs

Speed11 ms

Cameras—

Modelyolov6n

Version—

AcceleratorHailo-8L (M.2)price not tracked
Host—
CPU—

checked 2026-10-19Frigate docs

Intel N97 (iGPU)

OpenVINO (Intel)

Speed18.5 ms

Cameras8

Modelyolov9-t 320

Version0.17

AcceleratorIntel N97 (iGPU)price not tracked
HostIntel N97 mini PCprice not tracked
CPUIntel N97

Mar 19, 2026yanghu.github.io

Intel HD / UHD 630 (7th-9th gen iGPU)

OpenVINO (Intel)

Speed20–22 ms

Cameras—

Modelyolov9-t

Version—

AcceleratorIntel HD / UHD 630 (7th-9th gen iGPU)price not tracked
Host—
CPUIntel Core i5-8500T

Aug 25, 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

Intel UHD 770 (12th-14th gen iGPU)

OpenVINO (Intel)

Frigate docs

Speed16 ms

Cameras—

Modelyolov9-t 320

Version—

AcceleratorIntel UHD 770 (12th-14th gen iGPU)price not tracked
Host—
CPU—

checked 2026-10-19Frigate docs

2 other builds use the same device; the rest share the yolov9-t model family.