| Basic Specifications — Dimension | 495.60mm × 928.52mm × 88.80mm |
| Basic Specifications — Environment | Operating Temperature: 0ºC ~ 30ºC, Storage Temperature: -40ºC ~ 60ºC, Operating Humidity: 5% ~ 80%RH (non-condensing) |
| Basic Specifications — Power | 2 × 1300W hot-swappable power supplies, 1+1 redundancy support |
| CSD2-N128Q8550 — CSD2-N128R3576 — CSD2-N128R3588S | CSD2-N128SPK3 |
| Interface Specifications — Button | 1 × Power, 1 × UID, 1 × Recovery, 1 × Reset |
| Interface Specifications — Console | 1 × Console (RJ45, BMC debug serial port, baud rate 115200) |
| Interface Specifications — Display | 1 × VGA (maximum resolution 1080P, BMC management display) |
| Interface Specifications — Network | 8 × 10Gbps SFP+, 1 × Gigabit Ethernet (RJ45, MGMT is used as BMC management network) |
| Interface Specifications — USB | 3 × USB3.0, 1 × Type-C (OTG) |
| Physical Specifications — Installation requirements | IEC 297 Universal Cabinet Installation: 19 inches wide and 800 mm deep and above; Retractable slideway installation: The distance between the front and rear holes of the cabinet is 543.5mm~848.5mm |
| Software Specifications — AI Painting | K3: Supports private deployment of all image generation models; QCS8550: Supports private deployment of the Stable Diffusion image generation model |
| Software Specifications — BMC | The BMC management system is integrated with the web-based management interface, supporting Redfish, VNC, NTP, monitoring advanced and virtual media, and the BMC management system can be redeveloped |
| Software Specifications — Deep learning | All models: Support traditional network architectures such as CNN, RNN, LSTM, and support various deep learning frameworks such as TensorFlow, PyTorch, PaddlePaddle, ONNX, and Caffe. Support custom operator development and Docker containerization management technology |
| Software Specifications — Large language models | All models support private deployment of ultra-large-scale parameter models under the Transformer architecture, such as large language models including Deepseek-R1 Series, Gemma Series, Llama Series, ChatGLM Series, Qwen Series, Phi Series, etc. |
| Software Specifications — Vision large models | K3: Supports private deployment of all vision large models; QCS8550: Supports private deployment of vision large models including Qwen2.5-VL, InternVL3, etc. |
| Technical Specifications — AI computing power — 6144TOPS (48T × 128, INT8) — 768TOPS (6T × 128, INT8) | 7680TOPS (60T × 128, SquareINT4) |
| Technical Specifications — Architecture — ARM architecture | RISC-V architecture |
| Technical Specifications — Control nodes | Octa-core 64-bit processor RK3588, main frequency up to 2.4GHz, the highest computing power is 6TOPS |
| Technical Specifications — Fan module | 14 high-speed cooling fans |
| Technical Specifications — Number of nodes | 16 compute blades (128 distributed compute nodes) + 1 control node |
| Technical Specifications — Server form | 2U rack-mounted computing power server |