← All hardware
Google Coral USB Accelerator logo
hardware Edge & Robotics AI

Google Coral USB Accelerator

by Google (Coral)

Plug-and-play Edge TPU inference over USB for $59.99.

Pros

  • Dead-simple USB integration with any host
  • Very low power and silent operation
  • Cheap and well-documented for vision tasks

Cons

  • Locked to TensorFlow Lite / Edge TPU compiled models
  • Only 4 TOPS, eclipsed by newer accelerators
  • Aging platform with limited recent updates

✓ Where it shines / best for

  • Hobbyists and makers adding ML to Raspberry Pi / SBC projects
  • Prototyping low-power on-device vision inference
  • Education and learning edge ML with TensorFlow Lite

✕ Not the best fit for

  • Large models or generative AI / LLMs (limited memory and TFLite-only)
  • High-throughput multi-stream production analytics
  • Training workloads (inference only)

Features

  • ✓ On-device / offline
  • ✓ Real-time
  • ✓ Computer Vision
  • ✓ Low-power / efficient
  • ✓ Inference Accelerator
  • ✓ Raspberry Pi
  • ✓ Edge TPU
  • ✓ Open source
  • ✓ Tensorflow Lite
  • ✓ Usb Accelerator

Pricing

PlanPriceBillingNotes
Coral USB Accelerator$59.99one-timeSingle Edge TPU coprocessor via USB; sold through Coral/Mouseretailers

Pricing verified from the official source. Prices change often — confirm on the vendor's site before buying.

Specifications

power~2W (2 TOPS/W)
memoryHost-dependent (no large on-board DRAM)
interfaceUSB 3.0 (USB-C)
architectureGoogle Edge TPU ASIC
ai_performance4 INT8 TOPS
Sponsored

A full review is being generated for this product and will appear here shortly.

Compare with

Compare
Compare