Overview
AIO-OrinNX Jetson Orin NX Robotics Motherboard is an edge AI computer from Firefly built on Jetson Orin NX, rated by Firefly at 157 TOPS. It carries 16GB LPDDR5. Firefly publishes a fixed price for this configuration and sells direct.
Key Features
- AI compute: 157 TOPS
- Accelerator: Jetson Orin NX
- Memory: 16GB LPDDR5
- Storage: 1 x M.2 M-KEY (Expandable PCle NVMe SSD, supports 2242/2260/2280)
- OS: Jetson systems based on Ubuntu 22.04 provide a complete desktop Linux environment with graphics acceleration and support for libraries such as NVIDlA CUDA, TensorRT CuDNN, and more.
Ideal For
developers deploying vision or small-model inference at the edge on an ARM NPU rather than a GPU
Ai software stack
The NVIDIA Jetson Orin series delivers powerful Al compute power, massive unified memory, and a comprehensive software stack to power the latest generative Al applications. It enables fast inference on any generative Al model powered by the Transformer architecture, enabling superior edge performance on MLPerf.
Soc
NVIDIA Jetson Orin NX
Cpu
Octa-core 64-bit Arm Cortex-A78AE v8.2 processor, up to 2.0GHZ
Tpu
157 TOPS
Vpu
1024-core NVIDIA Ampere architecture GPU with 32 Tensor Cores
Ram
16GB LPDDR5
Storage
1 x M.2 M-KEY (Expandable PCle NVMe SSD, supports 2242/2260/2280)
Power
DC 12V (5.5 x2.1mm, support 9V~24V wide voltage input)
Power consumption
Normal: 7.2W(12V/600W)Max: 34.8W(12V/2900mA)
Video output
1 x HDMI2.0 (4K@60fps)
Video input
2 x MIPI CSI DPHY (1 x 4 Lanes or 2 x 2 Lanes), Line in (Led by double row headers)
Audio
1 x 3.5mm Audio jack (Support MC recording, American Standard CTlA)
Os
Jetson systems based on Ubuntu 22.04 provide a complete desktop Linux environment with graphics acceleration and support for libraries such as NVIDlA CUDA, TensorRT CuDNN, and more.
Dimension
122.89 mm x 85.04 mm x 35.28mm
Weight
Without Fan - 129g, with fan - 180g
Environment
Operating Temperature: -20℃~60°CStorage Temperature: -20°~ 70°CStorage Humidity: 10%~90%RH(non-condensing)
Other interface
1 x FAN(4Pin-1.25mm), 1 x SlM Card, 1 x Debug (3Pin-2mm),1 x Double-row pin headers (2x10-20PIN-2.0mm): USB2.0, SPl, 2 x 12C, Line in, Line out, GPl01 x Phoenix connector (2x4Pin,3.5mm pitch): 1 x RS485, 1 x RS232,1 x CAN 2.0
Button
1 x Reset, 1 x Recovery, 1 x Power
Robot model
ROS robot model is supported.
Large language models
Support Ollama local large model deployment framework, which can be used for natural language processing, code generation, and assistance scenarios. Support the private deployment of ultra-large-scale parametric models under the Transformer architecture, such as Llama3 and Phi-3 Mini.
Large visual models
Support the privatization deployment of large visual models such as EfficientViT, NanoOWL NanoSAM, SAM, and TAM.
Al Painting
Support ComfyUl graphical deployment framework, which can be used for scenarios such as image restoration, image style conversion, and image synthesis. Supports the private deployment of Flux, Stable Diffusion and Stable DiffusionXL image generation models in the AlGc field.
Operating Temperature
-20℃~60°C
Storage Temperature
-20°~ 70°C
Storage Humidity
10%~90%RH(non-condensing)
Area
Shipping time
Europe
3 - 7 business days
Asia, Oceania
3 - 7 business days
North America
3 - 7 business days
South America
5 - 10 business days
Brand
Firefly
Prices may vary. Verify on vendor site.
Quick Specs
- Ai software stack
- The NVIDIA Jetson Orin series delivers powerful Al compute power, massive unified memory, and a comprehensive software stack to power the latest generative Al applications. It enables fast inference on any generative Al model powered by the Transformer architecture, enabling superior edge performance on MLPerf.
- Soc
- NVIDIA Jetson Orin NX
- Cpu
- Octa-core 64-bit Arm Cortex-A78AE v8.2 processor, up to 2.0GHZ
- Tpu
- 157 TOPS
- Vpu
- 1024-core NVIDIA Ampere architecture GPU with 32 Tensor Cores
- Ram
- 16GB LPDDR5