AI Accelerator Cards

BVM provide a wide range of Industrial AI accelerator cards solutions for machine vision, machine learning and AI applications requiring additional processing power whilst maintaining a ruggedized design.

These cards typically integrate either a VPU (Vision Processing Unit), FGPA ( Field-Programmable Gate Array) or GPU (Graphics Processing Unit) and still retain the option where you can maintain a rugged design.

IEI Mustang AI Accelerator Cards: Accelerating AI Workloads
IEI Mustang TPU AI Accelerator Card
IEI Mustang FGPA AI Accelerator Card
IEI Mustang VPU AI Accelerator Cards
Neousys Frame Grabber Cards

Showing all 13 results

  • PCIe GL26

    Neousys PCIe-GL26 NVIDIA Jetson Xavier AI-enabled 6-port GMSL2 Camera Frame Grabber Card

    • Neousys PCIe-GL26 – AI-enabled 6-port GMSL2 Camera Frame Grabber Card
    • 6x GMSL2 FAKRA Z inputs supporting automotive GMSL2 cameras
    • Turnkey solution with pre-installed GMSL2 camera driver for selected cameras
    • Powered by NVIDIA® Jetson Xavier™ NX bundled with JetPack 4.6.1
    • 21 TOPS AI performance with up to 22 streams simultaneous 1080p@30FPS video encoding capability
    • x2 Gen3 PCI Express interface offering 10Gb/s total bandwidth
    • 1x GPS PPS input for frame sync calibration
    • 1x isolated CAN 2.0 and 1x RS232
    • -25°C to 60°C operating temperature with airflow

    Compare
  • PCIe NX154PoE

    Neousys PCIe-NX154PoE NVIDIA Jetson Orin 100 TOPS Frame Grabber Card with 4x PoE+ Ports

    • Neousys PCIe-NX154PoE – 100 TOPS Intelligent Frame Grabber Card with 4x PoE+ ports
    • Powered by NVIDIA® Jetson Orin™ NX bundled with JetPack 5.1
    • Single-slot half-length PCIe card form factor
    • 4x PoE+ 2.5 GbE ports with a 50W total power budget
    • 100 TOPS AI inference performance capable of up to four simultaneous streams of 4K@30FPS video decoding
    • 1x isolated RS-485 and 1x RS-232
    • x1 Gen2 PCI Express interface offering 2.5Gb/s
    • -25°C to 60°C operating temperature with airflow

    Compare
  • PCIe NX156U3

    Neousys PCIe-NX156U3 NVIDIA Jetson Orin 100 TOPS Frame Grabber Card with 6x USB 3.2 Ports

    • Neousys PCIe-NX156U3 – 100 TOPS Intelligent Frame Grabber Card with 6x USB 3.2 ports
    • Powered by NVIDIA® Jetson Orin™ NX bundled with JetPack 5.1
    • Single-slot width, standard PCIe half-length card form factor
    • 6x USB 3.2 ports, each port with user-configurable 900mA and 1500mA current limit
    • 100 TOPS AI inference performance
    • Software-programmable per-port power on/off control
    • 1x isolated RS-485 and 1x RS-232
    • x1 Gen2 PCI Express interface offering 2.5Gb/s total bandwidth
    • -25°C to 60°C operating temperature with airflow

    Compare
  • Mustang T100 T5 1

    IEI Mustang-T100-T5 Google Coral Edge TPU – ML Accelerator Card

    • IEI Mustang-T100-T5 Computing Accelerator Card with 5 x Google Coral edge TPU
    • 5 x Google Edge TPU ML accelerator
    • 20 TOPS peak performance (int8)
    • Host interface PCIe Gen2 x 4
    • Low-profile PCIe form factor
    • Support Multiple card
    Approximate 15W
    RoHS compliant

    Compare
  • Mustang F200

    IEI Mustang-200 – Celeron Computing Accelerator Card

    • IEI – Mustang-200-C-8G-R10 – Mustang-200 Dual Celeron Computing Accelerator Card
    • Dual 10Gbps network based x86 computing accelerator
    • Decentralized computing architecture for independent tasks
    • PCI Express x4 delivers scalable and flexible solution
    • Two Intel Core Celeron 3865U processors
    • Supports high-end graphics engine – Intel Iris Plus Graphics 650
    • Pre-installed 32 GB DDR4 (max. 64 GB) and 1 TB NVMe (max. 2 TB)

    Compare
  • Mustang F200

    IEI Mustang-200 – i5 Computing Accelerator Card

    • IEI – Mustang-200-i5-1T/32G-R10 – Mustang-200 Dual i5 Computing Accelerator Card
    • Dual 10Gbps network based x86 computing accelerator
    • Decentralized computing architecture for independent tasks
    • PCI Express x4 delivers scalable and flexible solution
    • Two Intel Core i5-7267 processors
    • Supports high-end graphics engine – Intel Iris Plus Graphics 650
    • Pre-installed 32 GB DDR4 (max. 64 GB) and 1 TB NVMe (max. 2 TB)

    Compare
  • Mustang F200

    IEI Mustang-200 – i7 Computing Accelerator Card

    • IEI – Mustang-200-i7-1T/32G-R10 – Mustang-200 Dual i7 Computing Accelerator Card
    • Dual 10Gbps network based x86 computing accelerator
    • Decentralized computing architecture for independent tasks
    • PCI Express x4 delivers scalable and flexible solution
    • Two Intel Core i7-7567U processors
    • Supports high-end graphics engine – Intel Iris Plus Graphics 650
    • Pre-installed 32 GB DDR4 (max. 64 GB) and 1 TB NVMe (max. 2 TB)

    Compare
  • mustang f100

    IEI Mustang-F100-A10 – FPGA Accelerator Card

    • IEI – Mustang-F100-A10 – FPGA Accelerator Card
    • PCIe FPGA Highest Performance Accelerator Card with Arria 10 1150GX support DDR4 2400Hz 8GB, PCIe Gen3 x8 interface
    • Half-Height, Half-Length, Double-Slot.
    • Power-efficiency, low-latency.
    • Supported OpenVINO toolkit, AI edge computing ready device.
    • FPGAs can be optimized for different deep learning tasks.
    • Intel FPGAs supports multiple float-points and inference workloads.

    Compare
  • Muxtang V100 MX1

    IEI Mustang-M2AE-MX1 – Vision Accelerator Card

    • IEI – Mustang-M2AE-MX1 – Vision Accelerator Card
    • Computing Accelerator Card with 1 x Intel® Movidius™ Myriad™ X MA2485 VPU,M.2 AE key interface, 2230, RoHS
    • Compact size M.2 2230 card. (22 x 30mm)
    • Low power consumption ,approximate 5W for one Intel Movidius Myriad X VPU.
    • Supported OpenVINO toolkit, AI edge computing ready device

    Compare
  • Mustang M2BM MX2

    IEI Mustang-M2BM-MX2 – Vision Accelerator Card

    • IEI – Mustang-M2BM-MX2 – Vision Accelerator Card
    • Deep learning inference accelerating M.2 BM key card with 2 x Intel® Movidius™ Myriad™ X MA2485 VPU, M.2 interface 22 mm x 80 mm, RoHS
    • Compact size M.2 2280 card. (22x80mm)
    • Low power consumption, approximate 7.5W for two Intel Movidius Myriad X VPU.
    • Supported OpenVINO toolkit, AI edge computing ready device
    • Two Intel Movidius Myriad X VPU can execute two topologies simultaneously.

    Compare
  • Muxtang V100 MX2

    IEI Mustang-MPCIE-MX2 – Vision Accelerator Card

    • IEI – Mustang-V100-MX2 – Mustang-MPCIE-MX2 – Vision Accelerator Card
    • Computing accelerator card with two Intel Movidius Myriad X VPU, providing a flexible AI inference solution
    • Compact size miniPCIe 30x50mm
    • Low power consumption ,approximate < 7W for two Intel Movidius Myriad X VPU.
    • Supported OpenVINO toolkit, AI edge computing ready device
    • Two Intel Movidius Myriad X VPU can execute Two topologies simultaneously.

    Compare
  • Muxtang V100 MX4

    IEI Mustang-V100-MX4 – Vision Accelerator Card

    • IEI – Mustang-V100-MX4 – Vision Accelerator Card
    • Computing Accelerator Card with 4 x Intel Movidius Myriad X MA2485 VPU, PCIe Gen 2 x 2 interface, RoHS
    • Compact size PCIe card. (113 x 56 x23 mm)
    • Low power consumption ,approximate 15W for four Intel® Movidius™ Myriad™ X VPU.
    • Supported OpenVINO™ toolkit, AI edge computing ready device
    • Four Intel® Movidius™ Myriad™ X VPU can execute four topologies simultaneously.

    Compare
  • MX8

    IEI Mustang-V100-MX8 – Vision Accelerator Card

    • IEI – Mustang-V100-MX8 – Vision Accelerator Card
    • Computing Accelerator Card with 8 x Movidius Myriad X MA2485 VPU, PCIe gen2 x4 interface, RoHS
    • Half-Height, Half-Length, Single-Slot compact size
    • Low power consumption ,approximate 2.5W for each Intel Movidius Myriad X VPU.
    • Supported OpenVINO toolkit, AI edge computing ready device
    • Eight Intel Movidius Myriad X VPU can execute eight topologies simultaneously.

    Compare