| Price | $700 |
|---|---|
| Category | NVIDIA Jetson |
| Availability | In stock |
| Delivery | Shipped across Lebanon, or collect from the lab |
A complete AI computer for the edge: the Jetson Orin Nano 8 GB module on NVIDIA's carrier board, heatsink and fan already fitted. A 1024-core Ampere GPU with 32 tensor cores and a 6-core Cortex-A78AE deliver up to 67 TOPS of INT8 inference against 8 GB of 102 GB/s LPDDR5 - enough to run object detection and small language models on the device, with no cloud round trip. Two MIPI CSI-2 camera connectors, an M.2 slot for an NVMe drive and a 40-pin GPIO header make it a serious base for vision robotics.
Key features
- 67 TOPS (sparse INT8) in Super mode - 40 TOPS on the original firmware
- 1024-core Ampere GPU with 32 tensor cores
- 6-core Arm Cortex-A78AE CPU, 8 GB LPDDR5 at 102 GB/s
- 2x MIPI CSI-2 camera connectors and DisplayPort 1.2
- 3x USB 3.2 Gen2, 3x USB 2.0, Gigabit Ethernet, 40-pin header
- Configurable 7W / 15W / 25W power modes, 19V supply
- Boots from microSD (64 GB or larger) or an NVMe drive via M.2 Key M
- Runs Ubuntu with NVIDIA JetPack, CUDA and TensorRT
Details
Specifications
| Model | NVIDIA Jetson Orin Nano 8GB Developer Kit |
|---|---|
| AI performance | 67 TOPS (sparse INT8), Super / MAXN mode |
| GPU | 1024-core NVIDIA Ampere, 32 tensor cores |
| CPU | 6-core Arm Cortex-A78AE v8.2, 64-bit |
| Memory | 8 GB 128-bit LPDDR5, 102 GB/s |
| Storage | microSD slot (64 GB UHS-1 or larger) + M.2 Key M for NVMe |
| Camera | 2 x MIPI CSI-2, 22-pin connectors |
| Display | 1 x DisplayPort 1.2 |
| USB | 3 x USB 3.2 Gen2, 3 x USB 2.0 |
| Networking | 1 x Gigabit Ethernet |
| Expansion | 40-pin header (UART, SPI, I2S, I2C, GPIO) |
| Power modes | 7W / 15W / 25W configurable |
| Power input | 19V DC supply |
| Module interface | 260-pin SO-DIMM |
| Dimensions | 100 x 79 x 21 mm |
| Software | NVIDIA JetPack (Ubuntu, CUDA, TensorRT) |
