Same-day dispatch before 2 PM · Free delivery over ₹999 · GST invoices Get the appPrices incl. GST
Geekobot
Snap & SendNEWGeeko AIWhere's myOrder
Log in
Products
  • Projects
    • Component guidesHow parts work, with code you can run
    • Learning pathsFrom your first LED to your first robot
    • Workshops & eventsOnline sessions for makers and classes
    • ElectrolarkFree guided builds, simulator and certificates
    • Students & teachersStudent discount and classroom help
    • CommunityShare builds and ask other makers
    • CalculatorsOhm's law, LED resistor, 555 and 100+ more
    • Circuit builderWire parts and run the circuit, powered by Electrolark
    • Geeko AIAsk what to buy or how to wire it
    • Snap & SendPhotograph a part or list, we find it
    • Part finderAnswer a few questions, get the right part
    • Compatibility checkWill these two parts work together?
    • Compare partsSpecs side by side
    • Business & bulk ordersGST invoices, credit and volume prices
    • Request a quotationSend your list, get a quote
    • Classroom kitsPer-student kits and lab bundles
    • Gift cardsFor students, teams and events
  • Atal Tinkering Lab
BOM to cart
Geekobot

Components, kits and know-how for makers, students, engineers, labs and businesses across India.

Ask Geeko AIOrders, parts and projects, any timeEmail supportReply within 1 working dayGet the Geekobot appAdd it to your home screen, free

Follow us

Shop

  • Boards & SBCs
  • Sensors & Modules
  • IoT & Wireless
  • Drone & FPV
  • 3D Printing
  • Filaments & Resins
  • Motors & Drivers
  • Power & Batteries
  • Semiconductors
  • Passive
  • Displays & LEDs
  • Switches & Relays
  • Wires & Cables
  • Prototyping
  • Tools & Test
  • Robotics
  • STEM Kits
  • Atal Tinkering Lab
  • Mechanical Parts
  • Audio

Orders

  • Track your order
  • Help & support
  • Shipping and delivery
  • Refunds and cancellation
  • Contact us

Learn

  • Projects
  • Geeko AI project assistant
  • Learning paths
  • Guides
  • Calculators
  • Electrolark: free guided builds

Part tools

  • Part finder
  • Compare parts
  • Will it work with my board?

Institutions

  • Classroom kits
  • Atal Tinkering Lab
  • Students & teachers
  • Workshops & Events

Business

  • Business & education
  • Request a quotation
  • BOM bulk upload
  • Quick order by SKU

Company

  • About Geekobot
  • Community
  • Gift cards
  • Terms & conditions
  • Privacy policy
  • Product directory
  • Sitemap

© 2026 Geekobot, a trade name of OLatus Systems Private Limited. All rights reserved.

20, 1st Floor, Neeladri Complex, 10th Cross, Sampige Rd, 2nd Main, Malleshwaram, Bengaluru, Karnataka 560003 · GSTIN 29AACCO0462F1ZM

+91 91810 15607 · connect@geekobot.in · Monday to Saturday, 10 AM to 2 PM IST

UPI · CARDS · NETBANKING · GST INVOICES

ShopProjectsGeeko AIGuides
Compare 0 parts →
Log in

Shop by category

Shop all components
  • Boards & SBCs1,910 products
    • Alternative Single Board Computers
    • Arduino Ecosystem
    • FPGA & Logic Boards
    • Microcontroller & Wireless Boards
    View all
  • Sensors & Modules4,701 products
    • Biomedical & Heart Rate
    • Current, Voltage & Power
    • Force, Weight & Pressure
    • Gas, Weather & Environmental
    View all
  • IoT & Wireless2,314 products
    • RF Modules
    • RFID & NFC
    • Antennas & RF Accessories
    • Cameras & Smart Vision
    View all
  • Drone & FPV3,558 products
    • Flight Control & Navigation
    • FPV Video & Optics
    • Frames & Structural Parts
    • Motors & Propulsion
    View all
  • 3D Printing2,204 products
    • 3D Printers
    • 3D Scanners & Digitizers
    • Laser Engravers & Cutters
    • Material Management & Upgrades
    View all
  • Filaments & Resins1,472 products
    • Filaments
    • Photopolymer Resins
    View all
  • Motors & Drivers463 products
    • BLDC Motor Drivers
    • DC & Geared Motors
    • DC Motor Drivers
    • Linear Actuators & Solenoids
    View all
  • Power & Batteries557 products
    • Battery Holders & Connectors
    • Breadboard Power
    • Chargers & BMS
    • DC-DC Converters
    View all
  • Semiconductors295 products
    • Diodes & Rectifiers
    • Interface & RF Encoder ICs
    • Logic ICs (74xx)
    • Logic ICs (CD4000)
    View all
  • Passive67 products
    • Capacitors
    • Circuit Protection
    • Crystals & Oscillators
    • Inductors
    View all
  • Displays & LEDs572 products
    • 7-Segment & Dot Matrix
    • Addressable LEDs
    • Character LCDs
    • Graphic LCDs
    View all
  • Switches & Relays184 products
    • Keypads & Touch
    • Push Buttons & Tactile
    • Relay Modules
    • Relays
    View all
  • Wires & Cables233 products
    • Board-to-Wire Connectors
    • Crimp & Splice
    • Headers & Dupont
    • Heat Shrink & Sleeving
    View all
  • Prototyping101 products
    • Breadboards
    • Interface Modules
    • PCBs & Perfboards
    View all
  • Tools & Test717 products
    • Bench Power Supplies
    • Hand Tools
    • Measuring Tools
    • Meters & Testers
    View all
  • Robotics180 products
    • Humanoid & Legged Robots
    • Robot Chassis & Platforms
    • Robotic Arms & Grippers
    • Wheels & Casters
    View all
  • STEM Kits268 products
    • Arduino Learning Kits
    • Coding & IoT Kits
    • Early Coding (Ages 3-8)
    • Invention Kits
    View all
  • Atal Tinkering Lab196 products
    • Package 1: Electronics, Robotics, IoT and Sensors
    • Package 2: Rapid Prototyping Tools
    • Package 3: Mechanical, Electrical and Measurement Tools
    • Package 4: Power Supply, Accessories and Safety Equipment
    View all
  • Mechanical Parts212 products
    • Bearings
    • Brackets & Mounts
    • Couplers
    • Fasteners & Standoffs
    View all
  • Audio109 products
    • Amplifier Modules
    • Buzzers & Sirens
    • Speakers
    View all
  1. Home
  2. ›Guides
  3. ›Boards & Microcontrollers
  4. ›Google Coral Edge TPU

Component guide · Advanced · 3 min read

Google Coral Edge TPU

Coral Dev Board Mini, M.2 B+M Key, M.2 A+E Key, M.2 Dual Edge TPU and Mini PCIe Accelerators and KKSB Coral Dev Board Case

By Geekobot Learning Team · Updated 29 Oct 2026

On this page
Short answerWhat the Google Coral Edge TPU: Dev Board Mini, M.2 and Mini PCIe accelerators isGoogle Coral Edge TPU: Dev Board Mini, M.2 and Mini PCIe accelerators pinoutWiring the Google Coral Edge TPU: Dev Board Mini, M.2 and Mini PCIe acceleratorsExample codeSetup and tuningWhat you needAlternatives and when to choose themCommon mistakesFAQsParts and next steps
Short answer

Coral boards run TensorFlow Lite models on Google's Edge TPU at about 4 TOPS using only 2W. The M.2 and Mini PCIe cards add the TPU to a PC, mini PC or single-board computer with a matching slot; the Dual Edge TPU card has two. The Dev Board Mini is a small Linux computer with the TPU built in. A very popular use is object detection in the Frigate camera recorder.

Key specs at a glance

Performance
4 TOPS per Edge TPU, about 2W
Cards
M.2 A+E, M.2 B+M, Mini PCIe, Dual Edge TPU (M.2 E-key)
Dev Board Mini
MediaTek 8167s, 2GB RAM, 8GB eMMC
Models
8-bit quantised TensorFlow Lite compiled for Edge TPU
OS
Linux (Debian/Ubuntu), Windows drivers for PCIe
Dual TPU
Needs a slot wired for two PCIe lanes to use both

Models in this guide

These are alternatives. Pick the one that fits your project; you only need one.

  • Option 1Google Coral Dev Board Mini G650-03324-01 Edge TPU AI SBC₹15,569
  • Option 2Google Coral Edge TPU M.2 B+M ML Accelerator Module₹3,659
  • Option 3Google Coral M.2 Accelerator with Dual Edge TPU₹7,869
  • Option 4Google Coral M.2 Edge TPU Accelerator A+E Key₹4,789
  • Option 5Google Coral Mini PCIe Edge TPU ML Accelerator₹4,389
  • Option 6KKSB Cases Google Coral Dev Board Case – Black/Grey Aluminum₹1,539
01

What the Google Coral Edge TPU: Dev Board Mini, M.2 and Mini PCIe accelerators is

Google Coral Edge TPU accelerators, in USB, M.2 and mini PCIe forms and on the Coral Dev Board, run TensorFlow Lite models fast at the edge, for example object detection on a Raspberry Pi.

Check your slot key before buying: A+E keys fit Wi-Fi slots, B+M keys fit SSD-style slots. Many boards wire only one PCIe lane to an E-key slot, so the Dual Edge TPU then works as a single TPU.

Install the gasket and apex drivers and the Edge TPU runtime, then use models from the Coral model zoo or compile your own quantised TFLite model with the Edge TPU compiler. In Frigate, set the detector type to edgetpu and the device to pci.

02

Google Coral Edge TPU: Dev Board Mini, M.2 and Mini PCIe accelerators pinout

The pins on the Google Coral Edge TPU: Dev Board Mini, M.2 and Mini PCIe accelerators and what each one does.

PinFunction
M.2 / mPCIe edgePCIe Gen2 x1 and power
USB-C (Dev Board Mini)Power and OTG
40-pin headerGPIO on Dev Board Mini
CameraMIPI CSI on Dev Board Mini
Heatsink padThermal contact
PinFunction
M.2 / mPCIe edge
PCIe Gen2 x1 and power
USB-C (Dev Board Mini)
Power and OTG
40-pin header
GPIO on Dev Board Mini
Camera
MIPI CSI on Dev Board Mini
Heatsink pad
Thermal contact
03

Wiring the Google Coral Edge TPU: Dev Board Mini, M.2 and Mini PCIe accelerators

Give the card airflow; the TPU slows down if it reaches its thermal limit.

Google Coral Edge TPU: Dev Board Mini, M.2 and Mini PCIe accelerators pinConnectionNote
M.2 cardHost M.2 slotMatch the key
Drivergasket-dkms + libedgetpuThen reboot
Frigatedetectors: edgetpu, device: pciIn config.yml
M.2 card
Connection:
Host M.2 slot
Note:
Match the key
Driver
Connection:
gasket-dkms + libedgetpu
Note:
Then reboot
Frigate
Connection:
detectors: edgetpu, device: pci
Note:
In config.yml
04

Example code

On newer kernels the gasket-dkms package may need building from the community-maintained source.

Install the PCIe Edge TPU driver and check the device (Debian/Ubuntu) · bash
echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | \
  sudo tee /etc/apt/sources.list.d/coral-edgetpu.list
curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -
sudo apt update
sudo apt install -y gasket-dkms libedgetpu1-std
sudo reboot

# After reboot the TPU should appear:
ls /dev/apex_0
05

Setup and tuning

Runtime

install the Edge TPU runtime and PyCoral; check which Python and OS versions are supported, because newer ones may need older Python.

Models

use models compiled for the Edge TPU (quantised int8 TFLite run through the Edge TPU compiler).

USB Accelerator

plug into a USB 3 port for full speed; USB 2 works but is slower.

M.2 and PCIe

install the gasket and apex drivers; check the slot key (A+E or B+M).

Cooling

the TPU throttles when hot; give it airflow in continuous use.

06

What you need

Shop this list6 of 6 found in our store · ₹37,814

  • Google Coral Dev Board Mini G650-03324-01 Edge TPU AI SBC: the part this guide coversGoogle Coral Dev Board Mini G650-03324-01 Edge TPU AI SBC₹15,569
  • Google Coral Edge TPU M.2 B+M ML Accelerator Module: another version this guide coversGoogle Coral Edge TPU M.2 B+M ML Accelerator Module₹3,659
  • Google Coral M.2 Accelerator with Dual Edge TPU: another version this guide coversGoogle Coral M.2 Accelerator with Dual Edge TPU₹7,869
  • Google Google Coral M.2 Edge TPU Accelerator A+E Key: another version this guide coversGoogle Coral M.2 Edge TPU Accelerator A+E Key₹4,789
  • Google Coral Mini PCIe Edge TPU ML Accelerator: another version this guide coversGoogle Coral Mini PCIe Edge TPU ML Accelerator₹4,389
  • KKSB Cases Google Coral Dev Board Case – Black/Grey Aluminum: another version this guide coversKKSB Cases Google Coral Dev Board Case – Black/Grey Aluminum₹1,539
07

Alternatives and when to choose them

  • ✓Edge AI boards: all accelerators compared.
  • ✓Raspberry Pi AI HAT: Hailo, more TOPS.
  • ✓Jetson modules: GPU-based AI.
08

Common mistakes to avoid

  • !Running an uncompiled TFLite model and expecting TPU speed.
  • !Using a newer Python than PyCoral supports.
  • !Plugging the USB accelerator into a USB 2 port.
  • !Running it hot with no airflow.
09

Frequently asked questions

Can I use the Coral USB Accelerator with a Raspberry Pi?

Yes. Install the Edge TPU runtime and PyCoral, and use a USB 3 port on the Pi 4 or Pi 5.

Can it run any TensorFlow model?

No. Models must be quantised to int8 TFLite and compiled with the Edge TPU compiler.

Why is my model slower than expected?

Some layers may not be supported and run on the CPU; check the compiler log.

Is the Coral still supported?

It works, but software updates are slow, so newer Python versions may need workarounds.

How fast is the Edge TPU?

Around 4 TOPS, enough for real-time object detection with MobileNet SSD models.

Parts for this guide

  • Google Coral Dev Board Mini G650-03324-01 Edge TPU AI SBC
    ₹15,569View
  • Google Coral Edge TPU M.2 B+M ML Accelerator Module
    ₹3,659View
  • Google Coral M.2 Accelerator with Dual Edge TPU
    ₹7,869View
  • Google Coral M.2 Edge TPU Accelerator A+E Key
    ₹4,789View
  • Google Coral Mini PCIe Edge TPU ML Accelerator
    ₹4,389View
  • KKSB Cases Google Coral Dev Board Case – Black/Grey Aluminum
    ₹1,539View
Shop AI & Edge Computing SBCs

Keep learning

Buying guideAdvancedEdge AI BoardsEdge AI boards run machine learning models on the device instead of in the cloud, for object detection, face recognition, voice commands and anomaly detection.3 min read · Boards & MicrocontrollersComponent guideIntermediateRaspberry Pi AI HAT+The AI HAT+ adds a Hailo neural network accelerator to the Raspberry Pi 5 through its PCIe port.3 min read · Boards & MicrocontrollersComponent guideAdvancedNVIDIA Jetson Modules and CarriersA Jetson is a small computer module with an NVIDIA GPU for running AI vision and robotics at the edge.4 min read · Boards & Microcontrollers

Sources

  • Coral documentation (coral.ai)
  • Frigate documentation

Written by the Geekobot team from manufacturer datasheets. Always check the datasheet for the exact part and variant you buy.

On this page
Short answerWhat the Google Coral Edge TPU: Dev Board Mini, M.2 and Mini PCIe accelerators isGoogle Coral Edge TPU: Dev Board Mini, M.2 and Mini PCIe accelerators pinoutWiring the Google Coral Edge TPU: Dev Board Mini, M.2 and Mini PCIe acceleratorsExample codeSetup and tuningWhat you needAlternatives and when to choose themCommon mistakesFAQsParts and next steps
Need a hand?Ask Geeko AI which part fits your project, or talk to the Geekobot team.Ask Geeko AIHelp & support

Parts for this guide6 items · ₹37,814

Google Coral Dev Board Mini G650-03324-01 Edge TPU AI SBC · Google Coral Edge TPU M.2 B+M ML Accelerator Module · Google Coral M.2 Accelerator with Dual Edge TPU · Google Coral M.2 Edge TPU Accelerator A+E Key · Google Coral Mini PCIe Edge TPU ML Accelerator · KKSB Cases Google Coral Dev Board Case – Black/Grey Aluminum

Ask the Community

Ask a question