Out Of Stock
CSB1-N4AGXOrin Jetson AGX Orin 1U AI Server
- Stock: Out Of Stock
- Model: csb1-n4agxorin-jetson-agx-orin-ai-server
- SKU: csb1-n4agxorin-jetson-agx-orin-ai-server
190 samples sold
$14,119.00
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
Product specifications and shipping information are referenced from the official Firefly (NVIDIA Jetson) product page.
No additional information available.
| Ai performance | Support the privatization deployment of ultra-large-scale parametric models under the Transformer architecture, such as Deepseek-R1 series, Gemma series, Llama series, ChatGLM series, Qwen series, Phi series and other large language models. Support the privatization deployment of large visual models such as EfficientVIT, NanoOWL, NanoSAM, SAM and TAM. Supports the private deployment of Flux, Stable Diffusion, and Stable Diffusion XL image generation models. Support Ollama local large model deployment framework and ComfyUI graphical deployment framework. Support for a variety of deep learning frameworks supported by cuDNN acceleration, including PaddlePaddle, PyTorch, TensorFlow, MATLAB, MXNet, Keras. Support custom operator development and Docker containerization management technology. |
|---|---|
| Server form | 1U rack-mounted computing power server |
| Number of nodes | 4 distributed computing nodes + 1 control node |
| Compute nodes | 12-core 64-bit processor NVIDIA Jetson AGX Orin (64GB), main frequency up to 2.2GHz |
| Control nodes | Octa-core 64-bit processor RK3588, main frequency up to 2.4GHz, the highest computing power is 6TOPS |
| Ai computing power | 1100TOPS (275T × 4, INT8) |
| Fan module | 6 high-speed cooling fans |
| Console | 1 × Console (RJ45, BMC debug serial port, baud rate 115200) |
| Ram | 64GB LPDDR5 × 4 |
| Storage | 64GB eMMC × 4 |
| Storage expansion | 3.5-inch/2.5-inch SATA3.0 SSD hard drive slot × 1 (Supports hot swapping; BMC can directly operate the hard drive, and computing child nodes can indirectly access the hard drive through the network sharing method provided by BMC) |
| Power | 550W AC power supply (Input: 90V AC~264V AC, 47 Hz~63 Hz, 8A; Hot swappable not supported) |
| Power consumption | Normal: 135W, Max: 400W |
| Display | 1 × HDMI (maximum resolution 1080P, BMC management display) |
| Weight | 494.0mm(L) × 469.3mm(W) × 44.4mm(H) |
| Environment | Operating Temperature: 0ºC ~ 40ºC, Storage Temperature: -40ºC ~ 60ºC, Operating Humidity: 5% ~ 80%RH (non-condensing) |
| Ethernet | 4 × 10G Ethernet (SFP+), 1 × Gigabit Ethernet (RJ45, MGMT is used as BMC management network) |
| Usb | 2 × USB3.0 (The lower USB is USB3.0 OTG, and the BMC can be upgraded OTG by using a USB flash drive) |
| Button | 1 × Reset, 1 × UID, 1 × Power |
No additional information available.
Our cooperating carriers: FedEx, DHL, UPS, SF Express
Delivery Area And Cost
| Country/Region | 0.0001-2kg | 2.0001-3kg | 3.0001-4kg | 4.0001-5kg | 5.0001-6kg | 6.0001-7kg | 7.0001-8kg | 8.0001-9kg | 9.0001-10kg |
|---|---|---|---|---|---|---|---|---|---|
| Japan, Taiwan, Hong Kong, Macau | $15 | $20 | $25 | $30 | $35 | $40 | $45 | $50 | $55 |
| Indonesia, Philippines | $25 | $30 | $40 | $50 | $60 | $70 | $80 | $85 | $95 |
| South Korea | $25 | $35 | $35 | $45 | $45 | $55 | $55 | $65 | $65 |
| Finland, France, Germany, Greece, Ireland, Italy, Netherlands, Norway, Portugal, Spain, Sweden, Switzerland, United States, Australia, New Zealand, Austria, Belgium, Denmark | $30 | $45 | $55 | $65 | $75 | $85 | $95 | $105 | $115 |
| Canada, United Kingdom | $40 | $50 | $60 | $75 | $85 | $95 | $105 | $115 | $130 |
| Hungary, India, Israel, Laos, Myanmar, Poland, Saudi Arabia, Turkey, United Arab Emirates, Vietnam, Bangladesh, Qatar, Cyprus, Pakistan, Brunei, Sri Lanka, Jordan, Oman, Maldives, Bulgaria, Iceland, Slovakia, Lithuania, Romania, Albania, Armenia, Mexico, Nepal, Serbia, Cambodia, Croatia, Czech Republic, Slovenia, Kazakhstan | $50 | $65 | $80 | $95 | $110 | $125 | $135 | $150 | $165 |
| Singapore, Thailand, Malaysia | $20 | $25 | $30 | $35 | $40 | $45 | $50 | $55 | $60 |
Shipping Time (for reference only, the actual situation shall prevail):
| 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 |
Please check which area your region/country is in.
Order preparation time: 3-7 business days (specific details need to refer to the order situation).