NF5468M6 is the latest flagship product in the flexible NF5468 AI server series, IEIT’s bestselling server. It supports the industry's most comprehensive Al accelerator card and domestic AI chips, and can be widely used with Internet AI public clouds, enterprise-level AI cloud platforms, smart security, video codecs, etc. NF5468M6 provides large local storage and is the industry's only single machine that can support one-click switching of Balance/Common/Cascade topology software to flexibly respond to the performance tuning requirements of different AI application scenarios.
Technical Specifications
| Model |
NF5468M6-P |
NF5468M6-T |
NF5468M6-V |
| Height |
4U |
| CPU |
2* 3rd Gen Intel® Xeon® IceLake Scalable processors, TDP 270W |
| GPU Accelerator Card |
Supports 8* FHFL DW PCIE GPU
Rear supports up to 4 PCIe4.0 x16 slots |
Supports 4* FHFL DW PCIE GPU
Rear supports 2 PCIe 3.0 x8 and 2 PCIe4.0 x8 slots |
Supports 16* FHFL SW GPU
Rear supports up to PCIe4.0 x16 slots |
| Chipset |
Intel® C621A series chipset ((LBG-R) |
| Memory |
32* DDR4 3200MHz LRDIMM/RDIMM |
| Internal PCIe |
Support up to 2* internal standard Raid card |
| Front I/O |
2* USB 3.0, 1* VGA, 1* RJ45 serial port |
| Rear I/O |
1* serial port, 2* USB 3.0, 1* RJ45 management port, 1OCP3.0(support NCSI) |
| Storage |
24* 2.5” or 12* 3.5” SAS/SATA drives(up to 8* NVME SSD), 2* M.2 SATA SSD |
16* 2.5” or 12* 3.5” SAS/SATA drives(up to 2* NVME SSD), 2* M.2 SATA SSD |
24* 2.5” or 12* 3.5” SAS/SATA drives(8* NVME SSD), 2* M.2 SATA SSD |
| RAID |
Optional supports RAID 0, 1, 10, 5, 50, 6, 60, etc., supports Cache super capacitor protection, provides RAID state migration, RAID configuration memory |
| OS |
Microsoft Windows Sever,Red Hat Enterprise Linux,Ubuntu Linux,CentOS, etc. mainstream OS |
| Cooling |
N+1 Redundant system cooling fan |
| PSU |
4* 1600W/2000W/2200W/3000W 80Plus platinum PSU, supports 2+2 redundancy |
| Dimensions (W*H*D) |
483mm * 175.5mm * 830mm |
| Temperature |
5 - 35°C / 41°F - 95°F |
| Full Load Weight |
≤85kg |
Key Features
Excellent Performance
2x Intel® 3rd Gen Xeon® Scalable processors, 3 UPI interconnects, TDP 270W
The PCIe Gen4 platform with doubled bandwidth can support up to 8x 350W GPU cards
4-card pass-through design, no need for PCIe Switch communication between CPU and GPU, greatly reducing P2P communication delays and helping algorithms achieve maximum performance
Flexible Configuration
Three GPU configurations to flexibly match different application scenarios
Supports one-click switching of Balance / Common / Cascade topology software to flexibly respond to the performance tuning requirements of different AI application scenarios.
Meets the needs of customers with high redundancy and high security scenarios, using rich I / O extension interfaces
Rich Ecology
Abundant global AI accelerator card partners, NVIDIA, AMD, Intel, etc.
Leading deep learning framework, TensorFlow, PyTorch, PaddlePaddle, MXNet, etc.
Powerful IEIT AIStation resource platform, algorithm platforms, and application optimization services
Mature meta-brain ecosystem for all-industry and all-scenario support
High Reliability
N+N power supply redundancy can carry 8x 350W GPUs running at full speed
N+1 fans redundancy ensures stable operation at high ambient temperatures
Smart BMC remote management provides zero-contact O&M, and improves O&M efficiency
Ваше сообщение должно содержать от 20 до 3000 символов!
Russian
