The CSB1-N4AGXOrin can be configured with up to four NVIDIA Jetson AGX Orin (64 GB) compute modules, providing up to 1100 TOPS (INT8) of computing power. It supports private deployments of mainstream AI models and various deep learning frameworks. The device is equipped with four 10 Gigabit Ethernet ports and supports expansion via SATA 3.0 hard drives.

• Product Datasheet: Click Here

Feature

• Private Deployment of AI Models: It supports private deployment of mainstream large-scale language models (such as Gemma, Llama, Qwen, etc.), large-scale visual models (such as EfficientVIT, SAM, TAM, etc.), image generation models (such as Flux, Stable Diffusion, etc.), and other large-scale models.
• Multiple Deep Learning Frameworks: Supports local large-scale models in Ollama and the ComfyUI graph deployment framework; compatible with various deep learning frameworks accelerated by cuDNN, including PaddlePaddle, PyTorch, TensorFlow, MATLAB, MXNet, and Keras; supports custom operator development and Docker containerization management technology.
• Video Encoding: Supports decoding up to 1 channel 8K@30fps, 3 channels 4K@60fps and 11 channels 1080P@60fps video, as well as encoding 2 channels 4K@60fps and 8 channels 1080P@60fps video.
• 4-port 10 Gigabit SFP+ Network Interface: It features four 10Gbps SFP+ Ethernet ports. Additionally, it includes a dedicated BMC management network interface for separating management and data traffic.
• Includes aBMC Management System: Equipped with an advanced aBMC intelligent management system. Supports secondary development based on customized needs.

Product Overview