Hardware
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.
[ 01 ]Pick a device
Which device to pick
- 01Light, CPU-only tasksRaspberry PiA small device next to a single camera for simple detection, counting and I/O.
- 02GPU-accelerated AI at the edgeNVIDIA Jetson (Orin or Thor)GPU acceleration for heavier models and several camera streams, on JetPack 6.2 or JetPack 7.2 for Jetson Thor.
- 03On the line or in the cabinetIndustrial PCWindows 11 or Ubuntu on a PC next to the machines, CPU or GPU depending on the workload.
- 04Many cameras, heavier modelsGPU serverA 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.
[ 02 ]Supported platforms
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 |
[ 03 ]Reva
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) |
See what Nara sees, on your own cameras.
Download Nara and build your first flow in minutes, or tell us what you need to see and do, and we’ll show you how it runs on your own hardware.