Configuration
Tailored to your project

Rack Servers
Model: ZH-6201/SW · SKU: 0102019
ZH-6201/SW is a 6U dual-socket server based on 4th/5th Gen Intel Xeon Scalable processors, supporting up to 8 GPU cards at 600W TDP each and flexible Switch expansion, suitable for AI, deep learning, smart education, smart city, healthcare, big data, HPC, virtual reality, media transmission and cloud gaming smart vision cloud applications.
Reference configuration
Tailored to your project
Fits your environment
Selection & delivery
WHY THIS PRODUCT
The ZH-6201/SW is an enterprise 6U GPU compute server based on dual 4th/5th Gen Intel Xeon Scalable processors, with up to 32 RDIMM/3DS modules at 5600 MT/s and support for up to 8 full-height full-length dual-width GPUs at 600W TDP each.
Dual 4th/5th Gen Xeon processors with up to 8 GPUs deliver top-tier compute performance.
Up to 32 RDIMM modules and 12 hot-swap drive bays for elastic scaling of business data.
N+N/N+M redundant power and DC-SCM 2.0 management ensure stable 7x24 operation.
| Processor | 2x 4th/5th Gen Intel Xeon Scalable processors |
|---|---|
| Memory | Up to 32x RDIMM or RDIMM-3DS modules, up to 5600 MT/s |
| Chipset | Intel C741 chipset |
| GPU | Up to 8 full-height full-length dual-width professional graphics or accelerator cards, 600W TDP/GPU |
| Network | 2x 1GbE RJ45 ports (i350-AM2), 1x OCP 3.0 NIC expansion slot |
| BMC | DC-SCM 2.0 management module with BMC AST2600 chip, IPMI2.0/Redfish support |
| PCIe Expansion | Passthrough GPU backplane supports 12x x16 standard PCIe slots; PCIe 5.0 Switch supports 13x x16 standard PCIe slots, up to 10 GPU cards |
| Storage | Supports different hot-swap drive configurations, up to 12x 3.5-inch SAS/SATA/NVMe (HDD/SSD) |
| Cooling | Supports 8x 8056 and 5x 8080 fan modules |
| Power | 8x CRPS power supplies, N+N/N+M redundant, optional 2000W/2700W |
| Operating System | Microsoft Windows Server / Linux / VMware ESXi |
| Environment | 0°C-35°C (operating temperature support varies by configuration) |
| Dimensions | 445 mm (W) x 265 mm (H) x 850 mm (D) |
| SKU | 0102019 |
| Warranty | - |
| Lead time | - |
Applications
Use this platform as part of a complete enterprise AI infrastructure solution.
A high-performance compute node supporting private model training, inference and concurrent workloads.
Contact our team →Serves AI, deep learning, smart city, healthcare and cloud gaming smart vision applications.
Contact our team →High-throughput I/O and low-latency interconnect for HPC, big data and virtual reality workloads.
Contact our team →Deployment
Move from requirement discovery to a validated configuration and supported delivery.
Confirm key parameters such as compute selection, power consumption, storage and facility environment.
Validate PCIe topology, thermal airflow and full-load system stability.
Provide factory test reports, environment pre-installation and full lifecycle technical support.
Resources
Request the current documents for the exact configuration your team is evaluating.
Review detailed technical specifications, dimensions and interface definitions.
Contact our team →Best practices for rack mounting, cabling and data center deployment.
Contact our team →Discuss customized solutions with TF NEW senior hardware engineers.
Contact our team →REQUEST A QUOTE
Tell us about your required configuration scale and deployment timeline, and we will provide professional advice and a formal quotation.