--- updatedAt: 2026-09-16T21:53:45.000Z agentTools: projectIndex: https://docs.sixfab.com/llms.txt --- # Overview The ALPON X5 AI edge computer delivers 25 TOPS of AI acceleration for real-time edge AI processing. It is built for industrial IoT and scalable edge computing applications. {`

The industrial edge AI computer.

ALPON X5 AI pairs a 25 TOPS DEEPX DX-M1 NPU with a Raspberry Pi Compute Module 5 host, multi-network connectivity, hardware root of trust, and centralized fleet management through ALPON Cloud. Built for real-time, on-device inference in production.

25 TOPS · DEEPX DX-M1 CES 2026 Best of Innovation Raspberry Pi CM5 LTE Cat 4 + eSIM 2× Gigabit Ethernet TPM 2.0 -20 °C to +60 °C
Quickstart Buy ALPON X5 AI
Sixfab ALPON X5 AI industrial edge AI computer with cellular and Wi-Fi antennas mounted on a rugged aluminum enclosure
ALPON X5 AI · Overview · Intelligented by DEEPX · Built on Raspberry Pi
What is the ALPON X5 AI?

ALPON X5 AI is Sixfab's industrial edge AI computer for production deployments. It runs on-device inference on a 25 TOPS DEEPX DX-M1 NPU, alongside a Raspberry Pi CM5 host (quad-core Cortex-A76 at 2.4 GHz), NVMe SSD, and always-online connectivity (2× Gigabit Ethernet, Wi-Fi, LTE Cat 4 with eSIM, Bluetooth 5.0 / BLE). The fanless aluminum enclosure operates from -20 °C to +60 °C at IP40 and is managed centrally through ALPON Cloud. Intelligented by DEEPX. Built on Raspberry Pi.

NPU
25 TOPS
INT8 · DEEPX DX-M1
Host CPU
2.4 GHz
Quad Cortex-A76 · Raspberry Pi CM5
Connectivity
4 paths
2× GbE · Wi-Fi · LTE Cat 4
Operating
-20 to +60 °C
Fanless aluminum · IP40

Key features

DEEPX DX-M1 NPU on board
A dedicated 25 TOPS at INT8 M.2 2280 module with on-chip memory. AI workloads run on the accelerator and never contend with the host CPU. Compile ONNX to DXNN and deploy with dxrt-runtime.
Raspberry Pi CM5 host
Broadcom BCM2712 quad-core Cortex-A76 at 2.4 GHz with 8 or 16 GB LPDDR4-4267 ECC SDRAM. Native Raspberry Pi ecosystem, Debian-based ALPON X5 AI OS, and ARM64 containers deployed through ALPON Cloud.
Always-online connectivity
2× Gigabit Ethernet, dual-band Wi-Fi, Bluetooth 5.0 / BLE, and LTE Cat 4 with integrated eSIM (eUICC SGP.22). Multi-path failover keeps the device reachable when one uplink degrades.
Hardware root of trust
Onboard Infineon SLB 9670VQ2.0 TPM 2.0 for secure key storage and measured boot. A hardware watchdog resets the system on failure, built for unattended industrial deployments.
Industrial form factor
Fanless aluminum enclosure, 100 × 100 × 45 mm at ~457 g, IP40. Operating range -20 °C to +60 °C, up to 95 % RH non-condensing. DIN rail and wall-mount kits available.
Managed by ALPON Cloud
Zero-touch onboarding, fleet inventory, OTA updates, container deployment, and remote terminal: one console for X4 and X5 AI fleets side by side.

How inference flows on ALPON X5 AI

Inference pipeline
Step 1
Capture
Cameras, sensors, and field devices stream data in over Ethernet, USB, MIPI CSI-2, or the GPIO add-on port (UART / I²C / SPI).
Step 2
Pre-process on CM5
Cortex-A76 handles resize, color conversion, and tensor packing before the NPU sees the frame.
Step 3
NPU inference
The DEEPX DX-M1 runs the compiled DXNN model. INT8 execution, fully on device.
Step 4
Act & forward
Outputs trigger local actions or stream events to ALPON Cloud. Frames stay on the device.
Why this matters

Inference runs fully on device. Only the events your application chooses to send leave the box, over Gigabit Ethernet, Wi-Fi, or LTE with automatic failover. Production fleets stay reachable, auditable, and within the privacy envelope of the site.

Where ALPON X5 AI fits

Computer vision & analytics
Real-time object detection, people counting, ALPR, defect detection, and smart-camera analytics, all on device.
Robotics & autonomy
AMR navigation, ROS / ROS 2 inference, multi-stream sensor fusion, and predictive maintenance loops.
Industrial AI infrastructure
Modbus and OPC-UA aggregation with AI scoring, anomaly detection on machine sensors, and PLC supervision with vision feedback.
Smart spaces & retail
Footfall analytics, queue and dwell-time tracking, shelf monitoring, and access control with face or plate verification.

Platform & ecosystem

Fleet management
Managed by ALPON Cloud

One console for ALPON X4 and ALPON X5 AI fleets. Onboard devices in minutes, push updates safely, deploy containers, and reach any device on the network, without leaving the browser.

Zero-touch onboarding OTA updates Container deployment Remote terminal Real-time monitoring
Explore ALPON Cloud Web console
Device comparison
ALPON X5 AI vs. ALPON X4

Not every workload needs an NPU. The ALPON X4 is the cost-effective IoT gateway for telemetry and protocol aggregation. The ALPON X5 AI adds on-device inference for vision and analytics.

Compute & NPU Memory Ports & I/O Connectivity Use cases
Compare devices Side-by-side

Related guides

Quickstart
Power on, connect, and claim the device in ALPON Cloud.
Specifications
Full datasheet values for compute, I/O, cellular, power, and compliance.
Physical Layout & I/O
Every port, LED, button, and antenna connector on each face of the enclosure.
Partnership lockups
Intelligented by DEEPX. Built on Raspberry Pi.

DEEPX silicon. Raspberry Pi host. Sixfab integration, software stack, ALPON Cloud, and field support, recognized as a CES 2026 Best of Innovation honoree.

`}