FAQ

ALPON X5 AI · FAQ · Hardware, NPU, connectivity, OS, and compliance
Frequently asked questions

ALPON X5 AI: frequently asked questions

Direct answers to the most common questions about the ALPON X5 AI industrial edge AI computer. Each entry is short and technical. For deeper reference, follow the linked pages on hardware, the DEEPX DX-M1 NPU, connectivity, or ALPON X5 AI OS.

What is the ALPON X5 AI?

The ALPON X5 AI is an industrial edge AI computer built by Sixfab. It pairs a Raspberry Pi CM5 (Cortex-A76 @ 2.4 GHz, up to 16 GB LPDDR4) with a DEEPX DX-M1 NPU rated at 25 TOPS at INT8 precision and 4 GB of dedicated on-chip memory. It ships with LTE Cat 4, dual-band Wi-Fi 5, dual Gigabit Ethernet, optional PoE+, and the ALPON Cloud fleet-management stack. The fanless aluminum enclosure is rated IP40 and operates from -20 to +60 °C.

Product & positioning

What problem does the ALPON X5 AI solve?

The ALPON X5 AI brings edge AI close to sensors and cameras so video does not need to stream to the cloud for inference. It runs computer-vision workloads (object detection, classification, segmentation, OCR, pose, face) at up to 25 TOPS on the DEEPX DX-M1 NPU while handling LTE, Wi-Fi, and Ethernet connectivity in a single fanless box.

How is the ALPON X5 AI different from the ALPON X4?

The ALPON X5 AI is the AI-capable successor to the ALPON X4. It adds a DEEPX DX-M1 NPU at 25 TOPS at INT8 precision, upgrades the compute to the Raspberry Pi CM5, and exposes an NVMe M.2 SSD slot. The ALPON X4 is an edge IoT computer based on the CM4 and ships without an AI accelerator.

FeatureALPON X4ALPON X5 AI
ComputeRaspberry Pi CM4Raspberry Pi CM5
AI acceleratorNoneDEEPX DX-M1 (25 TOPS)
StorageeMMCeMMC + NVMe M.2 SSD slot
CellularLTE Cat 4LTE Cat 4
Power input9 to 30 V DC, USB-C PD12 to 32 V DC, USB-C PD 27 W

For a full side-by-side comparison, see Compare ALPON Devices.

What are the top use cases for the ALPON X5 AI?

The ALPON X5 AI fits deployments where vision or sensor data needs to be processed locally with low latency and resilient connectivity:

  • Smart cities: traffic analytics, ANPR, pedestrian counting.
  • Retail: shelf monitoring, queue analytics, loss prevention.
  • Industry: defect detection, PPE compliance, line-of-sight safety.
  • Transportation: in-vehicle driver monitoring, fleet telematics with vision.
  • Agriculture and energy: remote assets monitored over LTE with AI triage at the gateway.
What is included in the box?

Every ALPON X5 AI ships with:

  • 1 × ALPON X5 AI edge AI computer
  • 1 × USB-C PD power adapter (15 V / 27 W)
  • 1 × 3-pin DC terminal block connector
  • 2 × LTE antennas, 1 × GNSS antenna, 1 × Wi-Fi / Bluetooth antenna
  • Quick-start card with QR-linked provisioning

DIN-rail and wall-mount brackets are optional accessories and are not included by default.

Can I swap an ALPON X4 with an ALPON X5 AI in an existing deployment?

In most cases yes, but verify three things first:

  1. Power: the ALPON X5 AI requires 12 to 32 V DC or 15 V USB-C PD. A 9 V supply is acceptable on the ALPON X4 but puts the ALPON X5 AI into restricted mode.
  2. Footprint: mechanical dimensions are close but not identical. Check mounting-hole positions before committing.
  3. Containers: rebuild every application container for ARM64 on the CM5 toolchain.
How do I buy or sample the ALPON X5 AI?

Order units and accessories from sixfab.com. For volume pricing, custom variants (PoE, memory, storage), or evaluation loaners, reach out through Sixfab contact.

Hardware & I/O

What is the main processor on the ALPON X5 AI?

The host compute is the Raspberry Pi CM5: a quad-core Cortex-A76 running at 2.4 GHz with up to 16 GB LPDDR4 memory and on-board eMMC. The CM5 handles the operating system, networking stack, and application containers, and feeds the DEEPX NPU over PCIe.

How does the NPU connect to the CM5?

The DEEPX DX-M1 sits on the CM5 PCIe bus as an M.2 module and appears as character device /dev/dxrt0 once the kernel driver loads. The NPU has its own 4 GB on-chip memory pool and does not share system RAM with the CM5.

What storage is available?

The ALPON X5 AI pairs the CM5's on-board eMMC (factory-flashed with ALPON X5 AI OS) with an internal NVMe M.2 SSD slot for user workloads, models, and logs. Typical variants ship with a pre-installed NVMe SSD; verify your SKU to confirm capacity.

What is the ADDON port, and can I plug Ethernet into it?

The ADDON port uses an RJ45 physical socket but is not Ethernet. It exposes 3.3 V GPIO with SPI, UART, and I2C for Sixfab add-on modules. Plugging an Ethernet or PoE cable into this port permanently damages the device.

Do not connect Ethernet or PoE to ADDON

This is the single most common installation mistake. The ADDON port is labeled on the enclosure. Use ETHERNET 0 or ETHERNET 1 for networking, and ETHERNET 0 only for PoE+ power.

Are ETHERNET 0 and ETHERNET 1 the same?

No. Use ETHERNET 0 for anything performance-sensitive or PoE-powered.

  • ETHERNET 0: native CM5 Gigabit PHY, PoE+ capable on applicable variants, the only port that accepts PoE power.
  • ETHERNET 1: Gigabit Ethernet bridged over USB 3.0 through the TUSB8020 hub. Shares upstream bandwidth with one of the USB 3.0 ports. Cannot accept PoE.
What do SW1 and SW2 on the enclosure do?

Two hardware switches are exposed for field configuration:

  • SW1 (Watchdog): ON enables the hardware watchdog, which resets the device if no keep-alive is received for 5 minutes. Software cannot override this switch.
  • SW2 (Boot / Burn): OFF is normal boot. ON is image-flashing mode, used only during supervised re-flashing.
Always power off before toggling SW1 or SW2

Changing SW2 while the device is powered can corrupt the CM5 eMMC.

Are the LEDs user-controllable?

One status LED is reserved for user applications. The remaining LEDs are driven by Sixfab system services (power, Sixfab Connect agent, cellular, Ethernet link).

Is there a TPM on the ALPON X5 AI?

Yes. The ALPON X5 AI includes a TPM 2.0 chip wired to the CM5 over SPI0. Use it from userspace with the standard tpm2-tools package:

terminal bash
sudo apt install -y tpm2-tools
tpm2_getcap properties-fixed

AI development & the DEEPX NPU AI

What AI model frameworks does the DEEPX Runtime support?

Train or obtain your model in any common framework — PyTorch, TensorFlow, Keras, XGBoost, MXNet — and export it to ONNX. The dx-com compiler then converts ONNX → DXNN. The DEEPX runtime loads only .dxnn artifacts.

Which model architectures run reliably on the DX-M1?

The DEEPX DX-M1 is optimized for image-based CNNs. Transformer architectures are not supported on the current runtime.

  • Object detection: YOLO v5, v7, v8, YOLOX; SSD variants
  • Classification: ResNet, MobileNet, EfficientNet
  • Segmentation: U-Net, semantic segmentation backbones
  • OCR: PaddleOCR-based pipelines
  • Face detection, recognition, pose estimation: CNN-based pipelines
What is the real-world FPS on popular models?

Throughput depends on the model variant, input resolution, and whether the model was compiled with PPU (post-processing unit) support. Indicative numbers for nano-class YOLO variants compiled with --ppu:

Input resolutionTypical FPS (YOLO nano, PPU on)
1280 × 720~50 FPS
1920 × 1080~20 to 25 FPS

Larger model variants trade FPS for accuracy. Benchmark your own pipeline; numbers vary with pre-processing, decoding, and rendering costs outside the NPU.

Can the NPU run multiple models at the same time?

Yes. The DEEPX runtime supports concurrent model execution on the DX-M1. Aggregate throughput is bounded by total NPU compute and the 4 GB on-chip memory footprint. Plan memory first, then latency.

What is the maximum model size the NPU can load?

The hard limit is the DX-M1's 4 GB on-chip memory. A .dxnn whose compiled footprint exceeds 4 GB will not load. If you hit the ceiling, recompile at a lower input resolution, switch to a lighter variant, or quantize before ONNX export.

Which programming languages can I use for inference?

The DEEPX runtime provides first-class bindings for Python and C++:

  • Python: dx_engine, bundled inside /usr/lib/libdxrt/dxrt-venv. Ideal for prototyping, OpenCV / GStreamer pipelines, and glue code.
  • C++: dxrt_api.h. Use this for deterministic latency, embedded pipelines, and production inference services.
How do I access the NPU inside a Docker container?

Map the character device into the container and run with --privileged:

terminal bash
docker run --rm --privileged   --device /dev/dxrt0   -v /opt/models:/models   alpon-infer:latest

For docker-compose, set privileged: true and devices: ["/dev/dxrt0"]. Build every image for ARM64.

How do I monitor NPU utilization and temperature?

Use dxtop, the DEEPX command-line monitor. It reports per-device utilization, memory use, and temperature in real time, similar to htop for CPUs or nvidia-smi for GPUs.

terminal bash
dxtop
# live NPU utilization, memory, and temperature

dxtop runs over SSH or in the Sixfab Connect remote terminal.

Can I control NPU power modes from software?

No. The DEEPX DX-M1 does not expose software-controlled performance or low-power profile switching on the current runtime. The NPU runs at a single operating profile.

Are example AI models or scripts pre-installed?

Pre-loaded example models are not bundled in the ALPON X5 AI OS base image. Reference pipelines (YOLOv8 detection, ResNet classification, U-Net segmentation) are published in the AI Development guide and the DEEPX Model Zoo, ready to pull into an ARM64 container.

Intelligented by DEEPX

Compile ONNX → DXNN with dx-com, ship the .dxnn in your container, and load it through dx_engine (Python) or dxrt_api.h (C++).

Connectivity & antennas

What network interfaces does the ALPON X5 AI expose?

The ALPON X5 AI ships with five independent network paths, all managed by the ALPON Cloud agent with automatic failover:

  • LTE Cat 4 (up to 150 Mbps DL / 50 Mbps UL, theoretical) with on-board eSIM (eUICC)
  • Wi-Fi 5 dual-band 2.4 / 5 GHz, IEEE 802.11 b/g/n/ac
  • Bluetooth 5.0 / BLE
  • Gigabit Ethernet × 2 (ETHERNET 0 native, ETHERNET 1 USB-bridged)
  • GNSS positioning (GPS + multi-constellation)
Which LTE bands are supported?

The cellular module covers a broad global band set:

B1 B2 B3 B4 B5 B7 B8 B12 B13 B18 B19 B20 B25 B26 B28 B34 B38 B39 B40 B41 B66

Connectivity on non-4G / LTE networks is not guaranteed. For full RF specs see Connectivity & Antenna Specifications.

Are the SMA antenna connectors male or female?

Connector genders are not uniform across ports. Match the antenna gender to the port when sourcing replacements.

PortLabelSMA connector
Wi-Fi / BluetoothWMale (RP-SMA)
GNSS/GPSGFemale
LTE MainLFemale
LTE DiversityLFemale
Does the ALPON X5 AI include an eSIM?

Yes. The ALPON X5 AI ships with an on-board, soldered eSIM (eUICC) that supports remote profile provisioning. Carrier switching and profile download are driven from Sixfab Connect, so the device can be activated without physical SIM handling.

Can I add an external outdoor antenna?

Yes. Sixfab offers an optional 3-meter IP67-rated outdoor combination antenna that covers LTE Main, LTE Diversity, Wi-Fi, and GNSS/GPS with surface mounting. Use it when the device is installed inside a metal enclosure or indoors away from windows.

Power & thermal

How do I power the ALPON X5 AI?

The ALPON X5 AI accepts three independent power inputs and draws from the highest-voltage source connected at any moment:

InputRangeMinimum wattage
DC terminal block12 to 32 V DC45 W at full load
USB-C PD15 V PD (sink only)27 W (45 W recommended)
PoE+37 to 57 V, IEEE 802.3at Class 425 W delivered

All three can be connected simultaneously, but using one source at a time simplifies diagnostics.

What happens if I power the ALPON X5 AI below 12 V?

The device enters restricted mode. The CM5, LTE modem, and both Ethernet ports stay active. The USB ports, PCIe bus (NVMe SSD and DEEPX DX-M1 NPU), ADDON port, and camera port are disabled. AI inference is not available in this mode because the NPU sits on the disabled PCIe bus. Restore ≥ 12 V to exit.

Does the ALPON X5 AI have a fan?

No. The ALPON X5 AI is fanless by design. The top aluminum surface is the primary heatsink for the CM5, the DEEPX DX-M1 NPU, and the voltage regulators. Mounting orientation materially affects sustained AI throughput; prefer upright or cooling-surface-up mounting.

What is the operating temperature range?

The ALPON X5 AI operates from -20 to +60 °C ambient and tolerates storage from -40 to +85 °C. Humidity is rated up to 95% non-condensing. The aluminum enclosure is classified IP40.

Does the ALPON X5 AI draw more power than the ALPON X4?

Yes under AI load. The CM5 plus DEEPX DX-M1 consume more than a CM4-only ALPON X4, which is why the minimum PD wattage is higher (27 W on the X5 AI versus 15 W typical on the X4) and a 45 W supply is recommended for peak inference. Idle and non-AI workloads are comparable.

Operating system & security

What operating system does the ALPON X5 AI run?

The device ships with ALPON X5 AI OS, a Sixfab-maintained 64-bit Debian-based Linux distribution for the Raspberry Pi CM5. It includes the DEEPX DX-M1 kernel driver, Docker, the Sixfab Connect agent, and the cellular and Wi-Fi stacks pre-installed. A future Yocto-based image is planned for long-term support.

What are the default credentials?

The default user is alpon with password sixfab.

Change the default password before production

The alpon / sixfab pair is shared across all devices. Run sudo passwd alpon on first boot. Do not delete the alpon user; it is required by Sixfab Connect and other system services.

How do I SSH into the device?

The hostname is derived from the MAC address as alpon-<MAC>, so you can reach it over mDNS on the local network:

terminal bash
# 1. By hostname (mDNS)
ssh alpon@alpon-<MAC>.local

# 2. Or by IP
ssh alpon@<DEVICE_IP>

When the local network is unavailable, use the browser-based remote terminal in Sixfab Connect. It works over cellular alone.

How do I update ALPON X5 AI OS?

Use the standard Debian tooling:

terminal bash
sudo apt update
sudo apt upgrade -y

Reboot if a kernel or firmware package was upgraded. For fleets, stagger rollouts one device at a time and watch ALPON Cloud for health reports before promoting the update.

Can I re-flash ALPON X5 AI OS myself?

The ALPON X5 AI OS image is factory-installed and is not distributed as a public download. If your device appears to need re-flashing, contact Sixfab support with the device serial number for the correct recovery procedure. Unguided re-flashing can brick the CM5 eMMC.

What security features are built in?

The ALPON X5 AI ships with a hardware-backed security foundation:

  • TPM 2.0 on SPI0 for sealed storage and secure boot keys
  • Factory-provisioned device identity bound to Sixfab Connect
  • Signed ALPON X5 AI OS packages delivered through authenticated APT repositories
  • Per-user SSH keys and password rotation through Sixfab Connect
  • Hardware watchdog (SW1) for autonomous recovery from hung services

ALPON Cloud & fleet management

What is Sixfab Connect?

Sixfab Connect is the fleet-management console for ALPON devices. It handles device registration, health monitoring, remote terminal access, container deployment, OTA updates, eSIM profile management, and network failover configuration. Every ALPON ships with a Sixfab Connect agent pre-installed.

How do I register an ALPON X5 AI?
  1. Open connect.sixfab.com and sign in.
  2. Scan the QR code on the device label, or select Manual registration and enter the serial number.
  3. Bind the device to an organization and asset group.
  4. Power the device on. First provisioning takes up to 3 minutes.

The device appears as Online once the Status LED turns solid green.

How do I deploy a containerized AI application?

Build your image for ARM64, push it to a registry that Sixfab Connect can reach, and schedule a deployment to the target device or asset group. Typical command for a local build:

terminal (host PC) bash
docker buildx build --platform linux/arm64   -t <your_registry>/alpon-infer:1.0   --push .

In Sixfab Connect, create a Deployment referencing that image and include the NPU device mapping (/dev/dxrt0) and the privileged flag.

Can I monitor NPU usage remotely from the cloud?

Yes. Open the device in Sixfab Connect and launch the remote terminal, then run dxtop. The terminal is a browser session bound to the cloud agent, so it works even if only cellular is up. Fleet-wide NPU metrics are on the roadmap; today the live view is per-device.

Warranty & compliance

What certifications does the ALPON X5 AI hold?

The ALPON X5 AI is certified or in progress for:

CE FCC IC UKCA RoHS WEEE REACH

Safety is tested against EN IEC 62368-1. EMC is tested against EN 55032 and EN 55035. Radio conformity covers EN 300 328, EN 301 511, EN 301 908-1, and EN 301 908-13. FCC is covered under 47 CFR Part 15 Subpart B and Subpart C.

What is the warranty period?

The ALPON X5 AI ships with a 2-year limited warranty against manufacturing defects under normal use. The warranty does not cover damage from out-of-range power, connecting Ethernet or PoE to the ADDON port, unauthorized modification, operation outside the rated environmental envelope, or physical and electrostatic damage.

What voids the warranty?
  • Supplying voltage outside the rated input range on the terminal block
  • Plugging Ethernet or PoE into the ADDON port
  • Opening the enclosure for reasons other than swapping the NVMe SSD or the DEEPX DX-M1 M.2 module (with ESD precautions)
  • Operating outside the -20 to +60 °C ambient envelope
  • Impact damage, liquid ingress, or ESD damage

See Safety & Compliance for the full list.

How do I dispose of an ALPON X5 AI at end-of-life?

The ALPON X5 AI complies with the EU WEEE directive. Do not dispose of it in unsorted household waste. Return the device through an authorized WEEE collection point, a local electronics recycler, or to Sixfab for responsible processing. Erase sensitive data from the NVMe SSD before disposal.

Question not answered here?

Run through the symptom-driven Troubleshooting guide before opening a support ticket.

Open Troubleshooting

Still have questions?

Reach out through any of the channels below. For technical diagnostics, bring the LED state and a support bundle collected with the commands in the Troubleshooting guide.