Skip to Content

Aetina Corporation · Edge AI Systems and GPU Accelerators

Aetina

Aetina is the pioneer in edge AI. With expertise in GPU accelerators, edge computing and system integration, it delivers field-ready, industrial-grade edge AI solutions. The range runs from palm-sized fanless Jetson systems and in-vehicle AI computers to GPU-expansion workstations, short-depth 2U servers and MXM / PCIe GPU cards.

Björn Tech is Aetina's authorised representative in Türkiye. We plan Aetina systems together with our enclosure, subrack and thermal solutions, and bring AI compute together with Innodisk storage, memory and cameras in the same project.

2012
Founded in Taiwan
2013
Joined the Innodisk Group
2022
Became an NVIDIA Elite Partner
ISO 9001
Certified 2015
2024
Intel Arc design partner

Applications

Aetina Solutions by Sector

Aetina systems complement the enclosure, subrack and thermal solutions we offer in every sector. Each sector page lists the recommended products and why they fit.

Edge AI Applications

For AI software companies: a 2U server, a GPU-expansion workstation and an agentic AI system to develop and test models in-house and run them at the customer site.

AEX-2UA2 · AIP-FR68S · AIP-RQ87

Recommended products

Medical

Agentic AI and 3D medical imaging inside the hospital: in reference deployments data stays on the hospital network and no separate server room is needed.

AIP-FR68 · AIP-SQ67 · M3A2000-VY

Recommended products

Industrial Automation

For AOI defect inspection, PoE-camera lines and cobots: AI that reduces false alarms, fanless PoE systems and Jetson Thor.

AIP-FR68 · AIE-PN33/43-4PSE · AIE-KT78/68

Recommended products

Measurement & Control

Compact, fanless systems for visual recognition and sensor fusion, maintained remotely through out-of-band management.

AIP-CR68 · AIE-PO22/32-S2

Recommended products

Railway & Transportation

In-vehicle AI for smart transportation: four GMSL2 cameras, ignition power control and wide-range DC input. Compliance with railway standards is assessed per project.

AIE-VN34/44-128-A1

Recommended products

Data Centre

Short-depth 2U rackmount servers: dual double-width GPUs, E1.S storage and redundant power.

AEX-2UA2 · AEX-2UA1

Recommended products

E-Mobility

A palm-sized in-vehicle system for surround-view monitoring and indoor autonomous mobile robots (AMRs): four GMSL2 cameras and E-Mark compliance.

AIE-VN34/44-128-A1

Recommended products

Technology

Designed for Demanding Conditions at the Edge

Aetina develops its GPU accelerators and edge systems for demanding temperature, vibration and maintenance conditions.

Wide Operating Temperature

Wide-temperature models for environments where commercial-grade GPGPU boards struggle; non-standard form factors are verified with Aetina's own interposer testing tool.

Fanless and Rugged

Fanless systems run silently and cut maintenance cost; the in-vehicle system is MIL-STD-810H compliant and E-Mark certified.

Remote Management

With EdgeEye, scattered edge AI devices are monitored from a laptop or smartphone; out-of-band (OOB) management adds remote reboot, shutdown, backup and recovery.

Wide Input Voltage

Input range up to 9-48 VDC on selected systems and ignition-based power control on the in-vehicle system.

Expandability

M.2 B/E/M-Key slots, PoE (PSE) ports, GMSL2 cameras and M.2 AI accelerators shape the system to the application.

Long-Term Availability

On selected GPU modules and cards the product pages state five years of availability.

Solutions

Ready-Made AI Solutions

Aetina's end-to-end solutions combine hardware and software integration in one service; the cards below link to the products each solution builds on.

AI Defect Inspection for AOI

Integrates with existing AOI systems; with NVIDIA Metropolis for Factories and Aetina's NVIDIA Certified System 3.0 AI computing platforms it reduces false alarms and manual re-inspection.

AIP-FR68

Product Card

On-Premises Agentic AI

A ready-to-deploy 2U edge system for AI agents and private LLMs, plus SuperEdge servers for generative AI, without the complexity of traditional AI infrastructure.

AIP-RQ87

Product Card

AI Vision on ARM

A Rockchip RK3588-based system adapts to evolving AI workloads through M.2 AI accelerator expansion.

AIE-KR1B-B1

Product Card

In-Vehicle AI

Palm-sized AI for harsh mobility with four GMSL2 cameras and ignition power control.

AIE-VN34/44-128-A1 | AIE-VO24/34-128-S1

Product Card

Product Series 01

Edge AI Inference Devices (DeviceEdge)

DeviceEdge systems bring AI inference to where the data is produced: palm-sized and fanless systems built on NVIDIA Jetson Thor and Orin modules, plus an AI-on-ARM system for flexible accelerator expansion. Variants add PoE camera ports, USB camera inputs and M.2 expansion.

AIE-KX13/23

NVIDIA Jetson AGX Orin · Fanless system

AIE-KX13/23

  • Supports NVIDIA Jetson AGX Orin™ 32GB/64GB module
  • Up to 275 TOPS of AI performance
  • Wide input voltage range from 9 to 36VDC
  • 1 x M.2 B-Key/1 x E-Key/1 x M-Key slot
  • 1 x GbE, 1 x 10GbE LAN port
  • Operating Temperature -25°C ~ +70°C
AIE-PX13/23

NVIDIA Jetson AGX Orin · Fanless system

AIE-PX13/23

  • Supports NVIDIA Jetson AGX Orin™ 32GB/64GB module
  • 1 x GbE port, 1 x 10GbE port
  • 1 x M.2 B-Key, 1 x M.2 E-Key, 1 x M.2 M-Key slot
  • Wide input voltage range from 9 to 36 VDC
  • Operating Temperature -25°C ~ +55°C
AIB-MX13/23

NVIDIA Jetson AGX Orin · Board-level system

AIB-MX13/23

  • Supports NVIDIA Jetson AGX Orin™ 32GB/64GB module
  • Up to 275 TOPS of AI performance
  • Wide input voltage range from 9 to 36VDC
  • 1 x M.2 B-Key/1 x E-Key/1 x M-Key slot
  • 1 x GbE/1 x 10GbE LAN port
  • Operating Temperature: -25°C ~ +80°C
AIE-KO22/32-S2 | AIE-KN32/42-S2

NVIDIA Jetson Orin NX / Nano · Super Mode

AIE-KO22/32-S2 | AIE-KN32/42-S2

  • Supports Super Mode for NVIDIA® Jetson Orin Nano™ /Orin™ NX
  • 1 x M.2 B-Key/E-Key/M-Key (NVMe 128GB built-in)
  • 2 x RJ-45 GbE Ports
  • Wide Input Voltage Range 12 to 24 VDC
  • Operating temperature -25°C ~ +70°C
AIE-PO22/32-S2 | AIE-PN32/42-S2

NVIDIA Jetson Orin NX / Nano · Fanless system

AIE-PO22/32-S2 | AIE-PN32/42-S2

  • Supports Super Mode for NVIDIA® Jetson Orin Nano™ /Orin™ NX
  • 1 x M.2 B-Key/E-Key/M-Key (NVMe 128GB built-in)
  • 2 x RJ-45 GbE Ports
  • Wide Input Voltage Range 12 to 24 VDC
  • Operating temperature -25°C ~ +55°C
AIB-MO22/32-S2 | AIB-MN32/42-S2

NVIDIA Jetson Orin NX / Nano · Board-level system

AIB-MO22/32-S2 | AIB-MN32/42-S2

  • Supports Super Mode for NVIDIA® Jetson Orin Nano™ /Orin™ NX
  • 1 x M.2 B-Key/E-Key/M-Key (NVMe 128GB built-in)
  • 2 x RJ-45 GbE Ports
  • Wide Input Voltage Range 12 to 24 VDC
  • Supports OOB (out-of-band) powered by Innodisk (optional)
AIE-PO23/33-3M | AIE-PN33/43-3M

NVIDIA Jetson Orin NX / Nano · Fanless system

AIE-PO23/33-3M | AIE-PN33/43-3M

  • Support NVIDIA Jetson Orin™ NX and Orin Nano™ (Super Mode-enabled) module
  • 2 x RJ-45 GbE ports
  • 1 x M.2 B-Key, 1 x M.2 E-Key slot
  • Wide input voltage range from 12 to 24 VDC
  • Operating Temperature -25°C ~ +55°C
  • Fanless Design
AIE-PN33/43-2PSE | AIE-PN33/43-4PSE

NVIDIA Jetson Orin NX · PoE camera ports

AIE-PN33/43-2PSE | AIE-PN33/43-4PSE

  • Support NVIDIA Jetson Orin™ NX 8GB/16GB module
  • 2 or 4 x IEEE 802.3af GbE PSE ports
  • 2 x GbE port, 2 x USB 3.2, 1 x OTG Type-C
  • 1 x M.2 B-Key, 1 x M.2 E-Key, 1 x M.2 M-Key slot
  • Wide input voltage range from 12 to 24 VDC
  • Operating Temperature -25°C ~ +55°C
AIE-PO23/33-6USB | AIE-PN33/43-6USB

NVIDIA Jetson Orin NX / Nano · USB cameras

AIE-PO23/33-6USB | AIE-PN33/43-6USB

  • Support NVIDIA Jetson Orin™ NX and Orin Nano™ (Super Mode-enabled) module
  • 6 x USB 3.2, 1 x OTG Type-C
  • 2 x RJ-45 GbE ports
  • 1 x M.2 B-Key, 1 x M.2 E-Key, 1 x M.2 M-Key slot
  • Wide input voltage range from 12 to 24 VDC
  • Operating Temperature -25°C ~ +55°C
AIE-CO23/33 | AIE-CN33/43

NVIDIA Jetson Orin NX / Nano · Mini series

AIE-CO23/33 | AIE-CN33/43

  • Supports NVIDIA® Jetson Orin Nano™ with Super Mode and Jetson Orin™ NX
  • 1 x M.2 B-Key/ E-Key/ M-Key (NVMe 128GB built-in)
  • 1 x RJ-45 for GbE
  • 2 x IEEE 802.3af GbE PSE Ports
  • Power Input Voltage Range 12 to 24 VDC
AIE-KT78/68

NVIDIA Jetson Thor · Robotics

AIE-KT78/68

  • Next-Gen AI Performance: Powered by NVIDIA® Jetson T5000™ / Jetson T4000™, delivering up to 2070 TFLOPS (FP4)
  • High-Speed Sensor Fusion: Supports QSFP28 (up to 100 Gbps) and 8x GMSL2 cameras for advanced vision AI
  • Industrial Connectivity: Equipped with dual 10GbE, 1GbE LAN support EtherCAT and 4x USB 3.2 Gen 2 ports
  • Rugged Reliability: Built for harsh deployments with 9-48VDC wide-range input and -25°C to +55°C operating temperature
AIB-AT78/68

NVIDIA Jetson Thor · Board-level platform

AIB-AT78/68

  • NVIDIA Blackwell GPU & 14/12 -Cores ARM Neoverse V3AE CPU
  • AI Power up to 2070/1200 FP4 TFLOPS
  • Support QSFP28 up to 100Gbps
  • Support EtherCAT
  • 4 x USB 3.2 Gen2
  • Wide range DC-in voltage
AIE-KR1B-B1

AI on ARM · Rockchip RK3588

AIE-KR1B-B1

  • Powered by Rockchip RK3588 8-Core 64-bit processor with an 8nm advanced process
  • LPDDR4X 16GB, eMMC 32GB
  • Flexible AI-on-ARM edge system with M.2 AI accelerator expansion
  • 2 x M.2 M-Key, one w/ PCIe 3.0 x4 for AI ASIC Accelerator, one w/SATA for Storage
  • 1 x M.2 E-Key for WIFI / BT, 1 x Mini PCIe for LTE
  • 1 x USB 3.2 Gen1, 1 x USB 2.0, 2 x GbE, 1 × COM, configurable for RS-232 / RS-485, 1 x HDMI 2.1

Product Series 02

In-Vehicle Edge AI Systems

A fanless, palm-sized in-vehicle system for harsh mobility: four GMSL2 cameras, ignition-based power control and wide-range DC input on an NVIDIA Jetson Orin NX / Orin Nano module.

AIE-VN34/44-128-A1 | AIE-VO24/34-128-S1

NVIDIA Jetson Orin NX / Nano · In-vehicle system

AIE-VN34/44-128-A1 | AIE-VO24/34-128-S1

  • Supports NVIDIA® Jetson Orin™ NX / Orin Nano™ with Super Mode
  • Supports up to 4 x GMSL2 cameras
  • Wide power input range 9 to 36 VDC
  • 1 x RJ-45 GbE port
  • Support M.2 E/M Key expansion
  • Operating Temp: -25°C ~ +55°C
  • MIL-STD-810H compliance
  • E-MARK
  • Isolated CAN FD
  • Dimensions: 132 x 136.3 x 61.5 mm (without wall-mount)

Product Series 03

AI Inference / Training Platforms (MegaEdge)

MegaEdge platforms pair Intel Core processors with GPU or M.2 AI accelerators: GPU-expansion AI workstations with PCIe Gen5, compact fanless M.2 systems for visual recognition, and MXM-based platforms.

MegaEdge · GPU-expansion AI workstation

AIP-FR68S

  • PCIe Gen5 x16 Support: Provides PCIe Gen5 x16 compatibility for the seamless integration of the latest NVIDIA® RTX PRO™ 6000 Blackwell Workstation Edition
  • Integrated Swappable 2000W Power Supply: Features an integrated, swappable 2000W power supply, ensuring sufficient capacity to support various PCIe GPUs and AI accelerator cards.
  • Built-In GPU Card Holder: Includes a built-in GPU card holder engineered to maintain optimal stability even in rugged operating conditions.

MegaEdge · PCIe series

AIP-FR68

  • Featuring with NVIDIA® RTX PRO™ 6000 Blackwell Max-Q Workstation Edition deliver strong performance for AI workload.
  • Specialized Thermal design to support Dual Qualcomm Cloud AI100 Ultra for localized AI Inference
  • Drive breakthrough AOI AI defect inspection with Metropolis for Factories.

MegaEdge · PCIe series

AIP-KQ67

  • Intel 12/13/14th Gen Core™ processors with Intel Q670E chipset
  • Supports 4x DDR5 U-DIMM up to 192GB
  • Support PCIe x16 graphics cards up to 300W paired with 850W PSU
  • Multiple and abundant expansion capabilities for WiFi, PoE, and storage modules
  • Supports Aetina EdgeEye for enhanced remote device management
  • Optional support for InnoAgent Out-of-Band module facilitates effortless remote maintenance

MegaEdge · MXM series

AIP-SQ67

  • Supports Intel 12/13th Gen Core™ i7/i5 processors, TDP up to 65W
  • 5 x DP++ (4 from MXM GPU Card, 1 from CPU)
  • 2 x M.2 M-Key NVMe/SATA
  • Built-in out-of-band (OOB) remote management module
  • Supports device remote monitoring via EdgeEye

MegaEdge · M.2 series

AIP-CR68

  • Intel 12/13th Gen Core™ i9/i7/i5 processors, TDP up to 35W
  • Build in Hailo-8™ AI accelerator for Edge AI inference
  • Support Out-of-Band (OOB) management for remote maintenance of edge devices

MegaEdge · M.2 series

AIP-MURE3/5/7-A1

  • Feature with 3x M.2 M-key for AI Accelerator cards,boosting extreme AI Inference performance.
  • Fanless & rugged chassis for harsh environment
  • Dual POE IP Camera support for real time video streaming
  • Support out-of-band (OOB) management tool for remote maintenance of edge AI system

Expansion kit · MXM

AIB-SQ67-A1

  • Supports Intel® 12th/13th/14th Gen Core™ i7/i5/i3 processors, TDP 125W
  • Intel® Q670E Chipset
  • 5x DP++(Support MST), 1 from Integrated Graphic, 4 from MXM graphic card
  • 5x 2.5G RJ45 LAN Ports
  • 6x USB 3.2 Gen2 x1 Type-A
  • 1x USB 3.2 Gen2 x2 Type-C

Product Series 04

AI Inference / Training Servers (SuperEdge)

Short-depth 2U rackmount servers for on-premises generative AI, LLMs and deep learning, plus a ready-to-deploy 2U edge agentic AI system.

AEX-2UA2

SuperEdge 2U · AI inference / training server

AEX-2UA2

  • Powered by Intel® Xeon® 6 processors with high performance cores.
  • Dual double-width GPUs for seamless generative AI, LLMs, and deep learning.
  • Flexible GPU support, including NVIDIA L40S, NVIDIA RTX PRO™ 6000 Blackwell Server Edition, NVIDIA H200 NVL, and NVIDIA RTX PRO™ Blackwell GPUs.
  • Compact 2U short-depth (420mm) rear-access rackmount server.
  • High-bandwidth architecture for fast, efficient data transfer in demanding enterprise tasks.
AEX-2UA1

SuperEdge 2U · AI inference / training server

AEX-2UA1

  • Single Intel® Xeon® 6700-series with P-cores.
  • 2U server - 420mm (16.5") short-depth rackmount server.
  • 1 x PCIe Gen5 x16 slot (FHHL) - supporting NVIDIA® BlueField® -3 or NVIDIA ConnectX® -7.
  • Up to 4x Hot-Swap PCIe Gen5 E1.S and 2x PCIe Gen5 M.2 slots.
  • 1+1 2000W Redundant Titanium level power supply.

MegaEdge · Enterprise 2U edge agentic AI system

AIP-RQ87

Kurumsal edge AI artık basit. AI ajanları, özel LLM'ler ve akıllı otomasyon için kullanıma hazır 2U edge ajan tabanlı AI sistemi; geleneksel AI altyapısının karmaşıklığı olmadan.

  • Intel® Core™ Ultra 5 / 7 / 9 Processors with Intel® Q870 Chipset

Product Series 05

AI Accelerators and GPUs (CoreEdge)

Embedded GPU modules in the MXM 3.1 form factor, an MXM module with four Hailo-8 processors, an MXM expansion kit and low-profile PCIe cards with Intel Arc and NVIDIA RTX graphics.

MX500B-QA · MX2000B-VA · MX4000B-WA · MX5000B-XA

CoreEdge MXM · NVIDIA RTX PRO Blackwell

MX500B-QA · MX2000B-VA · MX4000B-WA · MX5000B-XA

  • NVIDIA® RTX PRO™ 500 Blackwell Embedded GPU (MX500B-QA): 9.19 TFLOPS peak FP32 performance
  • NVIDIA® RTX PRO™ 2000 Blackwell Embedded GPU (MX2000B-VA): 13.78 TFLOPS peak FP32 performance
  • NVIDIA RTX PRO 4000 Blackwell Embedded GPU (MX4000B-WA)
  • NVIDIA RTX PRO 5000 Blackwell Embedded GPU (MX5000B-XA): 40.62 TFLOPS peak FP32 performance

CoreEdge MXM · NVIDIA RTX Ada Generation

MX2000A-VA · MX3500A-SA · MX5000A-WA

  • NVIDIA RTX 2000 Ada Generation Embedded GPU (MX2000A-VA, MXM 3.1 Type A): 3072 CUDA cores, 24 RT cores and 96 Tensor cores, 8GB GDDR6 memory, 12.99 TFLOPS peak FP32 performance
  • NVIDIA RTX 3500 Ada Generation Embedded GPU (MX3500A-SA): 23.04 TFLOPS peak FP32 performance
  • NVIDIA RTX 5000 Ada Generation Embedded GPU (MX5000A-WA): 9728 CUDA cores, 76 RT cores and 304 Tensor cores, 16GB GDDR6 memory, 41.15 TFLOPS peak FP32 performance
  • PCIe Gen 4 x16 interface
  • Error Correction Code (ECC) support (MX3500A-SA, MX5000A-WA)

CoreEdge MXM · NVIDIA RTX Ampere

M3A500-PP · M3A1000-PP · M3A2000-VY · M3A4500-WP

  • NVIDIA RTX A500 Embedded GPU based on Ampere architecture (M3A500-PP): 2048 CUDA cores, 16 RT cores and 64 Tensor cores, 4GB GDDR6 memory, PCIe Gen 4 x4 interface, 7.28 TFLOPS peak FP32 performance
  • NVIDIA RTX A1000 Embedded GPU based on Ampere architecture (M3A1000-PP): 2048 CUDA cores, 16 RT cores and 64 Tensor cores, 4GB GDDR6 memory, PCIe Gen 4 x8 interface
  • NVIDIA RTX A2000 Embedded GPU based on Ampere architecture (M3A2000-VY): 2560 CUDA cores, 20 RT cores and 80 Tensor cores, 8GB GDDR6 memory, 8.25 TFLOPS peak FP32 performance
  • NVIDIA RTX A4500 Embedded GPU based on Ampere architecture (M3A4500-WP)
  • Error Correction Code (ECC) support (M3A2000-VY, M3A4500-WP)

CoreEdge MXM · NVIDIA Quadro Turing

M3T1000-PN · M3T3000-QN · M3T5000-WN

  • NVIDIA Quadro T1000 embedded graphics based on NVIDIA Turing architecture (M3T1000-PN): 896 CUDA cores, 4GB GDDR6 memory, 2.6 TFLOPS peak FP32 performance
  • NVIDIA Quadro RTX3000 embedded graphics based on NVIDIA Turing architecture (M3T3000-QN): 1920 CUDA cores, 30 RT cores and 240 Tensor cores, 6GB GDDR6 memory, 5.3 TFLOPS
  • NVIDIA Quadro RTX5000 embedded graphics based on NVIDIA Turing architecture (M3T5000-WN): 3072 CUDA cores, 48 RT cores and 384 Tensor cores, 16GB GDDR6 memory, 9.4 TFLOPS
  • Support up to 4 DisplayPort 1.4 displays
  • Support CUDA Compute version 7.5, OpenCL 1.2, OpenGL 4.6, DirectX 12 and Vulkan 1.1 API
  • 5 year life cycle availability
MXA380E-QA

CoreEdge MXM · Intel Arc

MXA380E-QA

  • Intel Arc A380E GPU for the edge
  • 128 Intel® XMX Engines Cores, 8 Xe-cores, 8 Ray Tracing and 128 Xe Vector Engines, 6GB GDDR6 memory
  • PCIe Gen4.0 x8 signal
  • Five-year long-term product availability support
AI-MXM-H84W

CoreEdge MXM · Hailo-8

AI-MXM-H84W

  • 4 x HAILO-8 Industrial version
  • 104 TOPS INT8
  • Support -40°C~+85°C
  • TDP 25W (Typical)
  • MXM TYPE B

MXM expansion kit

DEV-MXM-4H-A1

  • Built based on PCI Express x16 Gen4, which converts the MXM slot to a PCI Express slot
  • Lets developers use the original PCIe system to test the compute performance of the MXM module in the early stage of a vision computing project

CoreEdge PCIe · Intel Arc A380E

IA380E-QUFL

  • Low-profile, single-slot and one-fan design
  • Equipped with Intel Arc A380E GPU for the Edge
  • High power efficiency to drive 2.56 TFLOPS peak FP32 performance
  • 6GB GDDR6, 4x Mini DisplayPort
  • PCIe Gen4 x16 Interface via golden finger
  • 5-year longevity support

CoreEdge PCIe · NVIDIA RTX 4060

N4060-VSFX

  • Powered by NVIDIA RTX 4060 Ada Lovelace architecture
  • 3072 CUDA cores, 24 RT cores and 96 Tensor cores, 8GB GDDR6 memory
  • PCIe Gen 4 x16 interface via golden finger
  • 15.11 TFLOPS peak FP32 performance

Software

Remote Management and OTA Updates

Field devices should be monitored, updated and recovered without a site visit. Aetina software brings this together for edge AI devices in a single management layer.

Remote Device Management Platform

EdgeEye

Centrally manage scattered edge AI devices from a laptop or smartphone: monitor hardware status such as CPU/GPU loading, memory utilisation and capacity, receive instant alerts and notifications, and use out-of-band (OOB) management for remote reboot, shutdown, backup and recovery.

OTA Updates

EdgeOTA

An integrated hardware and software system designed for OTA updates in edge computing environments; offered as EdgeOTA-Server software on the AIP-KQ67-A1 platform.

Source: aetina.com product pages and datasheets.

Why Björn Tech?

Integration in a Single System

We plan Aetina AI systems together with POLYRACK enclosures, our thermal management partners and Innodisk storage, memory and cameras as one project.

The Right Platform for the Application

A palm-sized fanless Mini system, a GPU-expansion workstation or a 2U server: we choose the platform with you based on what the application needs.

A Local Point of Contact

As the authorised representative in Türkiye we are your single point of contact for quotes, product selection and project support.

Talk to our engineering team about your project.

Contact Us