CSB1-N10R3588 1U Server 60T Large Model Privatization Deployment
Servers

CSB1-N10R3588 1U Server 60T Large Model Privatization Deployment

Firefly

Overview

CSB1-N10R3588 1U Server 60T Large Model Privatization Deployment is an AI inference server from Firefly built on RK3588, rated by Firefly at 60TOPS (INT8). Firefly publishes a fixed price for this configuration and sells direct.

Key Features

  • AI compute: 60TOPS (INT8)
  • Accelerator: RK3588
  • Storage: 256GB eMMC × 10 (Number of compute nodes)(Optional: 16GB/32GB/64GB/128GB/256GB)
  • Power: 550W AC power supply (Input: 90V AC~264V AC, 47 Hz~63 Hz, 8A) (Hot swappable not supported)

Ideal For

teams running on-premises inference for privately deployed models without buying datacenter GPUs

Server form

1U rack-mounted computing power server

Number of nodes

10 distributed computing nodes (up to 80 ARM cores) + 1 control node

Compute nodes

Octa-core 64-bit processor RK3588, main frequency up to 2.4GHz

Control nodes

Octa-core 64-bit processor RK3588, main frequency up to 2.4GHz, the highest computing power is 6TOPS

Ai computing power

60TOPS (INT8)

Fan module

6 high-speed cooling fans

Installation requirements

IEC 297 Universal Cabinet Installation: 19 inches wide and 800 mm deep and aboveRetractable slideway installation: The distance between the front and rear holes of the cabinet is 543.5mm - 848.5mm

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

Large model

Support the privatization deployment of ultra-large-scale parametric models under the Transformer architecture, such as Gemma-2B, ChatGLM3-6B, Qwen-1.8B, Phi-3-3.8B and other large language models

Deep learning

It supports traditional network architectures such as CNN, RNN, and LSTM, and supports the import and export of RKNN models; Support a variety of deep learning frameworks, including TensorFlow, TensorFlow Lite, PyTorch, Caffe, ONNX and Darknet. It also supports the development of custom operators

Console

1 × Console (RJ45, BMC debug serial port, baud rate 115200)

Soc

RK3588

Cpu

Octa-core 2.4GHz

Storage

256GB eMMC × 10 (Number of compute nodes)(Optional: 16GB/32GB/64GB/128GB/256GB)

Storage expansion

3.5-inch/2.5-inch SATA3.0/SSD hard drive slot × 1 (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)

Display

1 × VGA (maximum resolution 1080P, BMC management display)

Dimension

420.0mm(L) × 421.3mm(W) × 44.4mm(H)

Weight

Server net weight: 8.1kg, total weight with packaging: 10.3kg

Environment

Operating Temperature: 0ºC ~ 45ºCStorage Temperature: -40ºC ~ 60ºCOperating Humidity: 5% ~ 90%RH(non-condensing)

Internet

2 × 10G Ethernet (SFP+), 2 × Gigabit Ethernet (RJ45), 1 × Gigabit Ethernet (RJ45, MGNT 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 button

Other

1 × RS232 (DB9, baud rate 115200), 1 × RS485 (DB9, baud rate 115200)

Operating Temperature

0ºC ~ 45ºC

Storage Temperature

-40ºC ~ 60ºC

Operating Humidity

5% ~ 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

$8,919.00

Prices may vary. Verify on vendor site.

View on Firefly →

Quick Specs

Server form
1U rack-mounted computing power server
Number of nodes
10 distributed computing nodes (up to 80 ARM cores) + 1 control node
Compute nodes
Octa-core 64-bit processor RK3588, main frequency up to 2.4GHz
Control nodes
Octa-core 64-bit processor RK3588, main frequency up to 2.4GHz, the highest computing power is 6TOPS
Ai computing power
60TOPS (INT8)
Fan module
6 high-speed cooling fans

Tags

llm-inferenceedge-inferencecomputer-vision