Overview
Last updated
Was this helpful?
Last updated
Was this helpful?
We support any Edge AI Hardware that can run C++, and more!
You will find on this page a list of edge AI hardware targets that are either maintained by Edge Impulse or by our partners. During the integration and when possible, we leverage and integrate the hardware capabilities (optimized floating point units (FPU), DSP and Neural Network accelerations, GPU or other AI accelerators).
For the MCU-based hardware, depending on the integration we provide several or all of the following options:
A default Edge Impulse firmware, ready to be flashed on the hardware. The firmware capabilities depends on the integration (see also ).:
Data collection: Enables to to Edge Impulse Studio to simplify your getting started journey and ease the from some or all the sensors available.
Inferencing example: This includes the data sampling, extracting features using the signal processing blocks and run the inference using learning blocks.
and/or .
The open-source code for the firmware, which comes with documentation on how to build and compile the Edge Impulse firmware.
Examples on how to integrate your Impulse with your custom firmware, either using the or using libraries or components tailored for your hardware development environments. In our , search for the example-standalone-inferencing-%target%
Integrated deployment options to directly export a ready-to-flash Edge Impulse firmware packaged with your Impulse (including both the signal processing and the machine learning model).
Profiling (estimation of memory, flash and latency) available in Edge Impulse Studio and in the .
Extensive hardware testing, to make sure any improvements and changes in Edge Impulse will not break the current integration.
The hardware targets listed in this section are the perfect way to start building machine learning solutions on real embedded hardware. Edge Impulse's Solution Engineers and Embedded Engineers have a strong expertise with these hardware targets and can help on your integration. Feel free to .
If you just want to experience Edge Impulse? You can also use your !
(Linux | Industrial AI Camera with NVIDIA Orin NX)
(MCU | LoRaWAN Vision AI Sensor using Himax)
(MCU | Industry Reference Design using RA6M5)
(Cortex-M4F 192MHz)
(Cortex-M55 250MHz)
(RP2040 | Cortex-M0+ 200MHz)
(nRF52840 | Cortex-M4F 64MHz)
(nRF52832 | Cortex-M4 64MHz)
(STM32H747AII6 | Cortex-M7 480MHz)
(STM32H747XI | Cortex-M7 480MHz)
(STM32L4+ | Cortex-M4 120MHz)
(ESP32 | Xtensa LX6 240MHz)
(HX6537-A | ARC DSP 400MHz)
(PSoC63 | Cortex-M4F 150MHz)
(PSoC62 | Cortex-M4F 150MHz)
(nRF52840 | Cortex-M4F 64MHz)
(nRF5340 | Cortex-M33 128MHz)
(nRF9160 | Cortex-M33 64MHz)
(nRF9160 | Cortex-M33 64MHz)
(nRF9160 | Cortex-M33 64MHz)
(nRF7002 | Cortex-M33 128MHz)
(nRF5340 | Cortex-M33 128MHz)
(nRF9160 | Cortex-M33 64MHz)
(STM32H743II | Cortex-M7 480MHz)
(RTL8721DM | Cortex-M33 200MHz)
(nRF52840 | Cortex-M4 64MHz)
(RP2040 | Cortex-M0+ 200MHz, Xtensa LX6 240MHz, ESP32, nRF52840 | Cortex-M4F 64MHz)
(RP2040 | Cortex-M0+ 200MHz)
(RA6M5 | Cortex-M33 200MHz)
(RA8D1 | Cortex-M85 480MHz)
(HX6537-A | ARC DSP 400MHz)
(HX6537-A | ARC DSP 400MHz)
(nRF52840 | Cortex-M4F 64MHz)
(ESP32S3 | Xtensa LX7 240MHz)
(EFR32MG12 | Cortex-M4 40MHz)
(CXD5602 | Cortex-M4F 156MHz)
(STM32L4 | Cortex-M4 120MHz)
(CC1352P | Cortex-M4F 48MHz)
(Cortex-M55 + Ethos-U55 (multiple cores))
(Cortex-M4 + NDP120)
(RA6 + NDP120)
(Cortex-M33 78MHz + SiLabs MVP)
(Cortex-M55 + ST Neural-ART Accelerator)
(KA10000)
(NDP101)
(x86, M1, M2)
(x86_64)
(ARMv7 | Cortex-A72 1.5GHz)
(AM62x | Cortex-A53 1.4GHz)
(SAMA7G54 | Cortex-A7)
(RZ/G2L | Cortex-A55 1.2GHz)
(RZ/V2L | Cortex-A55 1.2GHz + DRPAI)
(x86_64 or AARCH64 + AKD1000)
(i.MX 8M Plus | Cortex-A53 1.8GHz + NPU)
(i.MX 93 | Cortex-A55 1.7GHz + NPU)
(x84_64 | MX3 5 TFLOPs)
(RZ/V2L | Cortex-A55 1.2GHz + DRPAI)
(QCS6490 | 2x Kryo 360 Gold @ 2.0 GHz + 6x Kryo 360 Silver @ 1.7 GHz + Hexagon 685)
(RZ/V2L | Cortex-A55 1.2GHz + DRPAI)
(RZ/V2H | Cortex-A55 1.8GHz + Dual Cortex-R8 + TVM/DRP)
(TDA4VM | Cortex-A72 + C7x 8TFLOPs)
(AM62A | Cortex-A53 + AI Accelerator 2 TFLOPs)
(AM68x | Cortex-A72 + AI Accelerator 8 TFLOPs)
(AARCH64 | Cortex-A78AE (NVIDIA Orin NX) + NVIDIA Ampere 1024 cores + 32 Tensor Cores)
(Nano: AARCH64 | Cortex-A57 + NVIDIA Maxwell 128 CUDA cores)
(AARCH64 | Cortex-A47 1.43 GHz + NVIDIA Maxwell 128 CUDA cores)