image 4 1
0
My Cart
Edge AI Expansion Board 22
Edge AI Expansion Board 23
Edge AI Expansion Board 15
Edge AI Expansion Board 16
Edge AI Expansion Board 12
Edge AI Expansion Board 19
Edge AI Expansion Board 26
Edge AI Expansion Board 25
Edge AI Expansion Board 27
Edge AI Exp. Board Dimension 1 1
Edge AI Exp. Board Dimension 2 1
Edge AI Expansion Board 22
Edge AI Expansion Board 23
Edge AI Expansion Board 15
Edge AI Expansion Board 16
Edge AI Expansion Board 12
Edge AI Expansion Board 19
Edge AI Expansion Board 26
Edge AI Expansion Board 25
Edge AI Expansion Board 27
Edge AI Exp. Board Dimension 1 1
Edge AI Exp. Board Dimension 2 1
SKU: S164 Category:

Edge AI Expansion Board for Raspberry Pi 5 

Build connected edge AI systems on Raspberry Pi 5.

Sixfab Edge AI Expansion Board combines DEEPX NPU acceleration, NVMe SSD storage, and LTE/5G connectivity in a single under-board platform designed for connected field deployments. Run fully on-device inference, store data locally at high speed, and stay always connected in the field without cloud dependency.

Price range: $60.00 through $190.00

Description

Intelligented by DEEPX

Sixfab Edge AI Expansion Board for Raspberry Pi 5

Turn your Raspberry Pi 5 into a full edge AI system. Add 25 TOPS of edge AI inference, NVMe storage, and LTE/5G connectivity to Raspberry Pi 5 in a single under-board stack.

25 TOPS · INT8 · DX-M1 M.2 NPU PCIe Gen 3 · Gen2/3 x1 Triple M.2 · AI + NVMe + LTE USB-C PD · 27 W min · 45 W recommended
For Raspberry Pi 5 only. Not Pi 4, CM4, or non-Pi SBCs.
View Documentation
25 TOPS INT8 · DX-M1 M.2 AI Module
PCIe Gen 3 Gen2/3 x1
Triple M.2 AI + NVMe + LTE
USB-C PD 27 W min · 45 W recommended

What is the Sixfab Edge AI Expansion Board?

The Sixfab Edge AI Expansion Board for Raspberry Pi 5 is a complete edge AI expansion platform that combines DEEPX NPU acceleration, NVMe SSD storage, and LTE/5G connectivity in a single board, powered through one USB-C connection that also back-powers the Raspberry Pi 5 through pogo pins.

Read the technical overview
One DEEPX NPU · Three edge AI form factors

Bring AI to the edge

The edge AI ecosystem for Raspberry Pi 5. One NPU, one SDK, three form factors for real-world deployment. Never rebuild your stack.

Sixfab AI HAT+ for Raspberry Pi 5

On-device AI

13 / 25 TOPS

AI acceleration for Raspberry Pi 5. Up to 25 TOPS of local AI performance. Plug in, install via APT, and start inferencing in minutes.

Sixfab AI HAT+ for Raspberry Pi 5 Learn More
Sixfab Edge AI Expansion Board This Product

Connected edge systems

25 TOPS · LTE/5G

Add LTE/5G connectivity, NVMe local storage, and multi-camera support for real field deployments in a single under-board stack.

Sixfab Edge AI Expansion Board You Are Here
ALPON X5 AI industrial edge AI computer

Industrial edge AI deployment

25 TOPS · −20 to +60 °C

Fanless, rugged, always-online edge AI computer for fleets and distributed industrial sites. Secure by design, IP40-rated, ALPON™ CLOUD-managed.

ALPON X5 AI Learn More
Built for connected edge AI systems

Key Features of the Edge AI Expansion Board

A unified Raspberry Pi 5 expansion platform that integrates AI acceleration, high-speed storage, and cellular connectivity for offline and connected edge AI deployments.

DEEPX NPU

Swappable M.2 AI module

DEEPX DX-M1 (25 TOPS at INT8) on a removable M.2 module. Bundled in Variant 2 · board-only in Variant 1.

AI Compute Interface

PCIe Gen 2 / Gen 3 x1

Dedicated PCIe lane for NPU ensuring stable high-throughput inference.

Storage & Connectivity

Triple M.2 architecture

Separate lanes for AI (PCIe), NVMe storage, and LTE/5G connectivity running in parallel.

Power System

USB-C PD

Single-cable power input that also back-powers Raspberry Pi 5 via pogo pins.

Software Stack

DXNN SDK + Model Zoo

Pre-compiled models or full ONNX → DXNN deployment pipeline.

AI Execution

On-device inference, no cloud

Fully offline AI processing with no cloud dependency.

How it works

A live pipeline · capture, infer, act, connect

Frames flow in from your cameras. The Pi 5 hosts your app. The DEEPX NPU runs the neural math. Results land locally on NVMe and stream over LTE/5G. Watch the data move.

Official Raspberry Pi Design Partner Intelligented by DEEPX
Confirmed specifications

Sixfab Edge AI Expansion Board: at a glance

The essentials. Every value here is sourced from R&D. For the full electrical, mechanical, and software reference, see the Hardware Reference docs.

Key specifications
AI acceleratorDEEPX DX-M1 · 25 TOPS at INT8 · on swappable M.2 module
NPU memory4 GB LPDDR5 @ 5600 MT/s on DX-M1 module
Host interfacePCIe Gen 2/3 ×1 over 40 mm FFC cable
M.2 slots3× M.2 · AI M-Key · NVMe M-Key · LTE/5G Key-B
NVMe storage2230/2242/2260/2280 · 380–440 MB/s read · 350–410 MB/s write
CellularM.2 Key-B · 1× nano SIM · eUICC supported
Power inputUSB-C PD · 27 W min · 45 W recommended
Pi back-power2× 5V + 2× GND pogo pins · 3 A per pin
Form factor88.46 × 89.19 mm · ~36.26 mm Z-stack with Pi 5
Operating temperature0–70 °C commercial
Supported hostRaspberry Pi 5
Host OSRaspberry Pi OS (Trixie)
Runtimedxrt-runtime · APT install · Python & C++ APIs
Model pipelineONNX → DXNN via DX-COM compiler
Hot-plugNot supported. Power off Pi 5 before mounting
From Edge to Action

Built for real-world edge AI

The Expansion Board is optimized for vision AI workloads that require local inference, LTE/5G connectivity, and high-speed data logging without relying on cloud-based AI processing.

Connected Smart Cameras

Run real-time object detection or face recognition on-device. Transmit metadata and alerts over LTE/5G. Raw video stays local. No cloud latency, no bandwidth bottleneck.

Robotics & Autonomous Drones

Equip mobile platforms with real-time vision AI and always-on cellular uplink. Make on-device decisions at full frame rate without depending on a cloud connection.

Outdoor Vision Systems

Count and classify vehicles, pedestrians, or wildlife from remote edge units. Aggregate metadata over cellular while keeping raw video fully on-device for privacy.

Remote Monitoring & Sensors

Monitor equipment or infrastructure in unattended environments. Run anomaly detection locally with the NPU and transmit only event-based alerts over LTE, cutting data costs dramatically.

IoT Sensor Fusion

Combine camera streams, sensor data, and telemetry for multi-modal edge inference. Store processed results locally on NVMe, sync summaries to the cloud on your schedule.

Live Field Testing & Staging

Validate AI models in real-world environments before ALPON X5 AI deployment. The Expansion Board runs the same DEEPX SDK and models, zero porting effort when you scale up.

Tested & certified

Compliance & certifications

Certification in progress
CE FCC UKCA RoHS REACH

Turn your Raspberry Pi 5 into a full edge AI system

Add 25 TOPS of edge AI inference, NVMe storage, and LTE/5G connectivity to Raspberry Pi 5 in a single under-board stack.

Quickstart View Documentation Contact

FAQ

Edge AI Expansion Board · Frequently asked questions

Frequently asked questions

Short answers to the most common questions about the Sixfab Edge AI Expansion Board for Raspberry Pi 5, the DEEPX NPU acceleration, NVMe storage, and LTE/5G connectivity stack, and how it compares to other Sixfab edge AI products.

Q How is it different from the Sixfab AI HAT+? ▾

The AI HAT+ is designed for early-stage AI prototyping with DEEPX NPU acceleration. Plug in, run your model, and validate the concept.

The Expansion Board is for engineers building systems that need to run in the field. Inference alone isn’t enough when you also need to log video locally, transmit alerts over cellular, and operate where there’s no Wi-Fi. The Expansion Board adds dedicated NVMe and LTE/5G M.2 slots alongside DEEPX AI acceleration, with all components running in parallel on the same board through a single USB-C connection.

Q Does it require cloud connectivity for AI inference? ▾

No. AI inference runs fully on-device using the DEEPX NPU.

The LTE/5G connection is used for transmitting metadata, alerts, or application-level outputs. AI processing does not depend on cloud connectivity, enabling fully offline inference workflows.

Q What AI models can I run? ▾

The platform supports models compiled for the DEEPX DX-M1 NPU family.

This includes YOLO-family models, pose estimation networks, and CNN-based architectures such as VGG-type models.

Custom models can be deployed using the DXNN SDK by compiling from frameworks such as ONNX and TensorFlow Lite.

The Sixfab Model Zoo also provides pre-optimized models ready for deployment.

Q Can I run multi-camera vision workloads? ▾

Yes. The Raspberry Pi 5 platform supports multi-camera configurations depending on system setup.

This enables use cases such as multi-angle monitoring, inspection workflows, and spatial vision applications.

Q How does NVMe storage help in edge AI? ▾

NVMe storage enables high-speed local data logging and buffering for AI pipelines.

It allows the system to:

  • Store datasets locally
  • Buffer inference results
  • Reduce reliance on cloud storage
  • Improve performance for continuous workloads

Q How does the Expansion Board fit into the Sixfab product line? ▾

The Edge AI Expansion Board is Stage 2 in a unified DEEPX NPU ecosystem:

  • Stage 1: AI HAT+ for rapid prototyping
  • Stage 2: Edge AI Expansion Board for connected field deployments
  • Stage 3: ALPON X5 AI for rugged industrial systems

All stages share the same software stack, allowing smooth scaling from prototyping to production deployments.

Q What is the difference between the Expansion Board and the ALPON X5 AI? ▾

Both systems use the same DEEPX NPU ecosystem.

The Edge AI Expansion Board is designed for Raspberry Pi 5-based deployments, making it ideal for development, testing, and connected field systems.

ALPON X5 AI is a fully integrated industrial edge AI computer with a rugged enclosure, extended temperature range, hardware reliability features, and fleet management capabilities for large-scale deployments.

Q Why would an engineer choose the Sixfab Edge AI Expansion Board over a standalone AI HAT for a field deployment? ▾

A standalone AI HAT handles inference. A field deployment also needs local data logging and a connectivity layer that doesn’t depend on Wi-Fi. The Expansion Board solves all on the same board: DEEPX NPU for inference, NVMe SSD for high-speed local storage, LTE/5G M.2 slot for cellular uplink. One USB-C cable powers the entire stack including the Pi 5.

Q What is the difference between running edge AI with the Expansion Board versus a cloud-connected setup? ▾

With a cloud-connected setup, raw video or sensor data leaves the device for remote processing — adding latency, bandwidth cost, and a dependency on network availability. The Expansion Board runs DEEPX NPU inference fully on-device. LTE/5G transmits only the output: metadata, alerts, or event triggers. Raw data never leaves the edge.

Contents

Edge AI Expansion Board · Package contents

What’s in the box

The Sixfab Edge AI Expansion Board ships in two variants. Both include the same complete mounting kit and assembly hardware. Variant 2 also bundles the DEEPX DX-M1 M.2 AI Module so you can run inference out of the box.

For Raspberry Pi 5 only. Not Pi 4, CM4, or non-Pi SBCs.

Variant 1

Board + mounting kit

Bring your own DEEPX DX-M1 M.2 AI module. Ideal if you already own one or want to choose the variant later.

1 AI Expansion Board ×1
2 USB 3.0 Bridge ×1
3 PCIe Cable ×1
4 M2.5 5mm M-F Plastic Spacer ×4
5 M2.5 15mm F-F Plastic Spacer ×6
6 M2.5 Screw ×6
7 USB Type-C Plastic Cap ×1
8 M2 Flathead Screw ×3
9 M2 Module Plastic Spacer ×3

Total 9 items

Recommended

Variant 2

Board + mounting kit + AI module

Includes the DEEPX DX-M1 M.2 AI Module (25 TOPS at INT8). Unbox, assemble, and run your first inference the same day.

1 AI Expansion Board ×1
2 USB 3.0 Bridge ×1
3 PCIe Cable ×1
4 M2.5 5mm M-F Plastic Spacer ×4
5 M2.5 15mm F-F Plastic Spacer ×6
6 M2.5 Screw ×6
7 USB Type-C Plastic Cap ×1
8 M2 Flathead Screw ×3
9 M2 Module Plastic Spacer ×3

10 DEEPX DX-M1 M.2 AI Module 25 TOPS · INT8 ×1

Total 10 items

Not included (sold separately)

The following are required or optional for a complete edge AI deployment but are not part of either variant:

  • Raspberry Pi 5 (host board, required)
  • USB-C PD power supply (27 W min, 45 W recommended, required)
  • DEEPX DX-M1 M.2 AI module (required for Variant 1, bundled in Variant 2)
  • NVMe SSD (M.2 2230, 2242, 2260, or 2280, optional for local storage)
  • LTE/5G M.2 modem module (M.2 Key-B, optional for cellular connectivity)
  • Nano SIM card (optional, only if using cellular)
  • Cellular antennas (optional, antenna connector type depends on the chosen modem module)
Rate Us

Your email address will not be published. Required fields are marked *

Your email address will not be published.

Need More Info
FAQ Contact Us
0
    0
    Your Cart
    Your cart is emptyReturn to Shop
    Continue Shopping
      Calculate Shipping
      Apply Coupon