---
lang: en
title: "Hardware for Nara: from edge devices to GPU servers"
url: https://nabrio.com/hardware
canonical: https://nabrio.com/hardware
updated: 2026-10-27
publisher: Nabrio Co., Ltd. (nabrio.com)
---

# Scales from a small edge device to a purpose-built server

The same Nara flows run on a Raspberry Pi or NVIDIA Jetson next to one camera, on an industrial PC, or on a GPU server handling many camera streams. A pilot on one device grows into a site-wide system without a rebuild.

## Which device to pick

- **Raspberry Pi** — Light, CPU-only tasks: A small device next to a single camera for simple detection, counting and I/O.
- **NVIDIA Jetson (Orin or Thor)** — GPU-accelerated AI at the edge: GPU acceleration for heavier models and several camera streams, on JetPack 6.2 or JetPack 7.2 for Jetson Thor.
- **Industrial PC** — On the line or in the cabinet: Windows 11 or Ubuntu on a PC next to the machines, CPU or GPU depending on the workload.
- **GPU server** — Many cameras, heavier models: A purpose-built server with NVIDIA GPUs for many camera streams and several flows in parallel.

Several devices can be paired into one site that shares data, so coverage grows by adding devices.

## Supported platforms for Nara

Minimum: 1 GHz quad-core CPU, 2 GB RAM, 8 GB storage. Eight CPU cores are recommended for busy flows. A GPU is recommended for multiple camera streams and heavier models.

| OS | Version | Architecture | GPU (CUDA) |
| --- | --- | --- | --- |
| Windows | Windows 11 | x86_64 | Supported |
| Linux | Ubuntu 22.04 / 24.04 | x86_64 | Supported |
| Linux | NVIDIA JetPack 6.2 (Jetson) | aarch64 | Supported |
| Linux | NVIDIA JetPack 7.2 (Jetson Thor) | aarch64 | Supported |
| Linux | Raspberry Pi OS (64-bit) | aarch64 | CPU only |

## Requirements for Reva

Reva runs on a Windows 11 workstation, with an NVIDIA GPU for training.

| Use | Minimum |
| --- | --- |
| Annotation only | 2 GHz quad-core CPU, 8 GB RAM, 500 MB plus dataset storage |
| Training | 2 GHz hexa-core CPU, 16 GB RAM, 10 GB storage, NVIDIA GPU (RTX 3060 / 8 GB VRAM or better recommended) |