Firefly EC-AGXOrin is an NVIDIA Jetson AGX Orin 64GB-powered AI inference system, similar to the AAEON BOXER-8645AI and Vecow RAC-1000 rugged Edge AI systems, and designed for edge AI applications such as in-vehicle computing, robotic control, machine vision, intelligent video analytics, and mobile robots.
The device features eight GMSL2 connectors (input via two 4-pin Mini FAKRA interfaces) and supports up to 22-channel 1080p or 8K, 30fps H.265 video decoding. It delivers 275 TOPS of AI performance through the NVIDIA module, and integrates 64GB LPDDR5 RAM, 64GB eMMC storage, and offers M.2 NVMe and MicroSD card storage options. Other ports include a 10GbE RJ45 jack, five GbE jacks, USB 3.0, HDMI 2.0, RS232, RS485, CAN, and the system also supports WiFi 6, Bluetooth 5.2, 4G/5G cellular connectivity, and GPS/GNSS.
Firefly EC-AGXOrin specifications:
- SoM – Jetson AGX Orin module with
- CPU – 12-core Arm Cortex-A78AE v8.2 64-bit processor with 3MB L2 + 6MB L3 cache
- GPU / AI accelerators
- NVIDIA Ampere architecture with 2048 NVIDIA CUDA cores and 64 Tensor Cores @ 1.3 GHz
- DL Accelerator – 2x NVDLA v2.0
- Vision Accelerator – PVA v2.0 (Programmable Vision Accelerator)
- AI Performance – Up to 275 TOPS (INT8) @ 60W
- Video Encode – 2x 4K60 | 4x 4K30 | 8x 1080p60 | 16x 1080p30 (H.265)
- Video Decode – 1x 8K30 | 3x 4K60 | 7x 4K30 | 11x 1080p60| 22x 1080p30 (H.265)
- System Memory – 64GB 256-bit LPDDR5 @ 204.8 GB/s
- Storage – 64GB eMMC 5.1 flash
- Storage
- M.2 2280 M-Key socket supports 2280 NVMe SSDs
- MicroSD card slot
- Video Output – HDMI 2.0 port up to 4K at 60Hz
- Camera interfaces – 8x GMSL2 (Gigabit Multimedia Serial Link 2) with FAKRA connectors compatible
- Audio – 3.5mm audio jack (Support MIC recording, CTIA)
- Networking
- 10GbE RJ45 port
- 5x Gigabit Ethernet RJ45 ports
- Optional WiFi and Bluetooth via M.2 socket (see Expansion section)
- Optional 4G LTE via Mini PCIe socket (see Expansion section) and SIM card slots
- Optional 5G through M.2 B-KEY
- Optional GNSS support (I’d assume through the 4G LTE module?)
- 7x antenna holes
- USB
- 4x USB 3.0 Type-A ports
- 2x Type-C USB ports with debug and OTG support
- Serial – 1x RS-232 and RS-485 via phoenix connector
- Expansion
- M.2 2230 E-Key socket for WiFi/BT
- M.2 B-Key socket for 4G LTE
- M.2 2280 M-Key socket for NVMe SSD
- Mini PCIe socket for 4G support
- 8x DIO via DB-9 connector
- Phoenix connector (2×12-pin, 3.5mm pitch) with 1x RS485, 1x RS232, 2x CAN 2.0, 1x UART, IO, 3.3V & 5V pins
- Misc
- Power, Reset, and Recovery buttons
- Run and Power LED indicator
- Power Supply – 24V DC via 5.5 × 2.1mm DC jack
- Dimensions – 277.95 × 136.09 × 88.0mm
- Temperature Range – Operating: -20°C to 60°C; storage: -20°C to 70°C
- Humidity – 10 ~ 90%, non-condensing
Firefly mentions that the device runs Ubuntu 22.04 and offers a full desktop Linux environment with graphics acceleration and support for CUDA, TensorRT, and cuDNN libraries. It supports ROS-based robotics models like DeepSeek-R1, Llama, ChatGLM, Qwen, and Phi, and vision models like EfficientViT, NanoSAM, and TAM. It also runs local image generation models, including Flux and Stable Diffusion XL, making it suitable for edge-based AI, robotics, and creative applications.
The system also supports Ollama for running large models locally, ComfyUI for visual AI workflows, and deep learning frameworks like PyTorch, TensorFlow, MATLAB, and PaddlePaddle, all accelerated by cuDNN. It also supports custom operator development and Docker containerization, simplifying deployment and updates. At this point, I’d normally mention that more details are available on the Wiki page and that all the necessary software can be found in the product’s download section, but it seems those are still being worked on.
Previously, e-con Systems introduced the NVIDIA Jetson Xavier AGX kit supporting up to six cameras with 15-meter cables. The Firefly EC-AGXOrin can be seen as an upgrade, featuring a more powerful Jetson AGX Orin module and support for up to eight GMSL2 camera inputs.
Firefly has yet to provide pricing information for the EC-AGXOrin AI inference system. More information can be found on the product page.
Debashis Das is a technical content writer and embedded engineer with over five years of experience in the industry. With expertise in Embedded C, PCB Design, and SEO optimization, he effectively blends difficult technical topics with clear communication
Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress. We also use affiliate links in articles to earn commissions if you make a purchase after clicking on those links.
