LogoLogo
AI HubCommunityWebsite
  • Start Here
  • AI Hub
    • Overview
    • Quickstart
    • Teams
    • Device Farm
    • Browser Inference
    • Model Zoo
      • Hailo
      • Intel
      • MemryX
      • BrainChip
      • Google
      • DeGirum
      • Rockchip
    • View and Create Model Zoos
    • Model Compiler
    • PySDK Integration
  • PySDK
    • Overview
    • Quickstart
    • Installation
    • Runtimes and Drivers
      • Hailo
      • OpenVINO
      • MemryX
      • BrainChip
      • Rockchip
      • ONNX
    • PySDK User Guide
      • Core Concepts
      • Organizing Models
      • Setting Up an AI Server
      • Loading an AI Model
      • Running AI Model Inference
      • Model JSON Structure
      • Command Line Interface
      • API Reference Guide
        • PySDK Package
        • Model Module
        • Zoo Manager Module
        • Postprocessor Module
        • AI Server Module
        • Miscellaneous Modules
      • Older PySDK User Guides
        • PySDK 0.16.0
        • PySDK 0.15.2
        • PySDK 0.15.1
        • PySDK 0.15.0
        • PySDK 0.14.3
        • PySDK 0.14.2
        • PySDK 0.14.1
        • PySDK 0.14.0
        • PySDK 0.13.4
        • PySDK 0.13.3
        • PySDK 0.13.2
        • PySDK 0.13.1
        • PySDK 0.13.0
    • Release Notes
      • Retired Versions
    • EULA
  • DeGirum Tools
    • Overview
      • Streams
        • Streams Base
        • Streams Gizmos
      • Compound Models
      • Result Analyzer Base
      • Inference Support
  • DeGirumJS
    • Overview
    • Get Started
    • Understanding Results
    • Release Notes
    • API Reference Guides
      • DeGirumJS 0.1.3
      • DeGirumJS 0.1.2
      • DeGirumJS 0.1.1
      • DeGirumJS 0.1.0
      • DeGirumJS 0.0.9
      • DeGirumJS 0.0.8
      • DeGirumJS 0.0.7
      • DeGirumJS 0.0.6
      • DeGirumJS 0.0.5
      • DeGirumJS 0.0.4
      • DeGirumJS 0.0.3
      • DeGirumJS 0.0.2
      • DeGirumJS 0.0.1
  • Orca
    • Overview
    • Benchmarks
    • Unboxing and Installation
    • M.2 Setup
    • USB Setup
    • Thermal Management
    • Tools
  • Resources
    • External Links
Powered by GitBook

Get Started

  • AI Hub Quickstart
  • PySDK Quickstart
  • PySDK in Colab

Resources

  • AI Hub
  • Community
  • DeGirum Website

Social

  • LinkedIn
  • YouTube

Legal

  • PySDK EULA
  • Terms of Service
  • Privacy Policy

© 2025 DeGirum Corp.

On this page
  • Package contents
  • Hardware requirements
  • System requirements
  • Installation procedure
  • Preparing your system
  • Installing the Orca M.2 Accelerator Module
  • Reassembling the system
  • Software setup
  • Driver installation
  • PySDK setup
  • Thermal management and overheating protection
  • Troubleshooting
  • Module not detected
  • Performance issues

Was this helpful?

  1. Orca

Unboxing and Installation

This page features unboxing and installation instructions for the Orca M.2 Accelerator Module in M.2 form factor.

The Orca M.2 Accelerator Module is a high-performance AI accelerator that allows application developers to create sophisticated, real-time edge AI solutions. It supports pruned model processing, model multiplexing, and typically consumes under 4 W, making it an ideal choice for energy-efficient edge AI applications.

Package contents

Upon opening the package, ensure that the following items are included:

  • Orca M.2 Accelerator Module

Hardware requirements

Before installing the Orca M.2 Accelerator Module, verify that your system meets the following requirements:

System requirements

  • Host platforms:

    • x86-64 or ARM Aarch-64

    • Available M-Key M.2 Slot (M.2-2280 Form Factor)

  • Operating system:

    • Linux Ubuntu 20.04, 22.04, and 24.04

Installation procedure

Preparing your system

1

Power off your system and disconnect it from the power supply to ensure safety.

2

Open your system’s casing to access the M.2 slot. Ensure that you locate the M-Key M.2 slot (M.2-2280).

Installing the Orca M.2 Accelerator Module

1

Insert the module into the M.2 slot at a 30-degree angle. Ensure that the connector aligns properly with the slot.

2

Gently press the module down and secure it with a compatible screw. Be careful not to over-tighten the screw to avoid damaging the module.

3

Check that the module is securely fastened and seated properly in the slot.

Reassembling the system

1

Once the module is installed, close the casing of your system.

2

Reconnect all power cables and peripherals.

Software setup

Driver installation

PySDK setup

Thermal management and overheating protection

To ensure optimal performance, the Orca M.2 Accelerator Module operates within specified thermal limits. please refer to the datasheet.

In a few cases, a heatsink or fan may not be required. If you experience overheating, consider installing a heatsink or fan. The module will automatically reduce operating frequency to cool down if the junction temperature exceeds the limit.

Troubleshooting

Module not detected

  • Ensure the module is properly seated in the M.2 slot.

  • Verify that your power system meets the hardware requirements and that drivers are correctly installed.

Performance issues

  • Check thermal management, as overheating can lead to throttling.

  • Ensure that all software dependencies are properly installed.

PreviousBenchmarksNextM.2 Setup

Last updated 2 months ago

Was this helpful?

Install the necessary drivers for the Orca M.2 Accelerator Module. You can download, build, and install the driver following the instructions in .

Download and install the DeGirum PySDK by following the instructions in .

For recommended cooling solutions, please refer to .

Orca M.2 Setup
PySDK Installation
Thermal Management