4U 8GPU Server for Deep Learning Workloads



Inspur NF5488M5 is pioneering AI server supporting eight NVIDIA V100 Tensor Core GPUs interconnected with ultra-high bandwidth NVSwitch in a 4U form factor. NF5488M5 is designed to facilitate a variety of deep learning and high-performance computing applications, including voice recognition, video analysis and intelligent customer service.

Hands-on with an 8x NVIDIA Tesla V100 SXM3 Server with NVSwitch

STH In-Depth Review of NF5488M5 »


Extreme Performance

8*NVIDIA V100 Tensor Core 32GB GPUs with 5,120 Tensor Cores, delivering up to 1 petaFLOPS of AI computing performance

The option of two 28-core CPUs to provide top-level, general-purpose computing performance

Easy to Deploy

6KW in 4U, a design make it easy to deploy in a wide spectrum of data center scenarios, especially for power-constrained racks

Flexible GPU cluster expansion over PCIe fabric


Designed to operate on 54VDC, a more power-efficient voltage for GPUs

A multi-layer heat dissipation design and intelligent PID adjustment that provide industry-leading thermal management and control


Model NF5488M5
HGX-2 Base Board *SXM3 GPU NVLink, up to 350-400W TDP, NVSwitch Full Connection
NVIDIA® Tesla® Volta, Volta Next (SXM3)
Processor 2*Intel® Xeon® Scalable Processors, 3*UPI
Performance 1 petaFLOPS
Memory 24× DDR4 DIMM, 6 Channel
Storage 8 x 2.5” SATA storage (Includes 4*2.5” NVMe), 2*M.2
PCIe 4 x PCIe x16 for 100G NIC,1x PCIex8 for 50G NIC / NVMe
Fan & Cooling Redundant Hot swap System Fan, Air cooling
PSU 2+2 Redundant, up to 6 KW total
Chassis 4U W*H*D 448mm*175.5mm*850mm

Interested in learning more?