top of page
server-parts.eu

server-parts.eu Blog

Special Offer: New Supermicro SYS-420GP-TNAR+ with 8× NVIDIA A100 80GB — Only €55,000!

  • Writer: server-parts.eu server-parts.eu
    server-parts.eu server-parts.eu
  • Oct 14
  • 4 min read

Updated: 3 days ago

The Supermicro SYS-420GP-TNAR+ is a 4U rackmount GPU server designed for extremely demanding workloads such as AI training, deep learning, and HPC (High-Performance Computing). It is built around dual Intel Xeon Scalable CPUs and an NVIDIA HGX A100 platform with 8 GPUs.


Supermicro SYS-420GP-TNAR+: Only €55,000

✔️ 3-Year Warranty – No Risk: Pay Only After Testing


Think of it as a smaller version of a supercomputer. It combines strong CPU performance, ultra-fast GPU communication, and high-speed NVMe storage.


Supermicro SYS-420GP-TNAR+ 4U GPU server with 8× NVIDIA A100 80GB SXM4 GPUs, dual Intel Xeon CPUs, 512GB DDR4 memory, and NVMe storage for AI, deep learning, and HPC workloads. server-parts.eu. refurbished. used.

Supermicro SYS-420GP-TNAR+ 4U GPU server with 8× NVIDIA A100 80GB SXM4 GPUs, dual Intel Xeon CPUs, 512GB DDR4 memory, and NVMe storage for AI, deep learning, and HPC workloads.


Hardware Overview: Supermicro SYS-420GP-TNAR+


Component

Details

Motherboard

X12DGO-6-P

GPUs

8× NVIDIA A100 80GB SXM4 (on NVIDIA Delta HGX baseboard)

CPUs

2× Intel Xeon Silver 4314 – 16 cores @ 2.4 GHz (32 cores total)

Memory

8× 64 GB DDR4-3200 RDIMM (512 GB total)

Storage

2× 1.9 TB NVMe PCIe 4.0 (2 DWPD) + 2× 960 GB NVMe PCIe 4.0 (1 DWPD, TCG Opal)

Networking

Intel X550 AIOM – 2× 10 GbE RJ45

Power Supply

4× 3000 W Titanium redundant PSUs

Condition / Warranty

New • 3 Years Supermicro Warranty • In Stock • €55,000 (EXW)



System Architecture: Supermicro SYS-420GP-TNAR+


Dual Xeon CPUs

Each CPU handles up to 8 memory channels and communicates through Intel UPI. The Silver 4314 models provide a total of 32 cores. For heavier AI or HPC tasks, you can use Gold or Platinum CPUs (up to 40 cores / 270 W TDP).


Memory

The system has 32 DIMM slots (16 per CPU) that support up to 8 TB DDR4 RAM or 12 TB with Optane PMem 200. The installed Silver CPUs limit memory speed to 2667 MT/s, while the modules are capable of 3200 MT/s.


GPU Board

The NVIDIA HGX A100 baseboard connects 8x A100 80GB SXM4 GPUs with NVLink + NVSwitch. This setup provides each GPU with approximately 600 GB/s connection to others, allowing them to function almost as a single large GPU. Each A100 operates at up to 400 W and supports MIG (Multi-Instance GPU), which is useful for dividing GPUs into smaller tasks.


PCIe & Expansion

The server includes 10 PCIe 4.0 x16 slots (5 per CPU). This supports additional network cards (25/100 GbE or InfiniBand), storage HBAs, or accelerator cards. The included AIOM slot carries the Intel 10 GbE NIC.


Storage

The front features 6 hot-swap 2.5″ bays (SATA/SAS/NVMe). It has 2 × NVMe U.2 (1.9 TB each) for data and 2 × M.2 (960 GB each) for the boot OS. RAID 0/1/5/10 is possible for SATA drives via Intel RSTe.


Power and Cooling

Four 3000 W PSUs (2+2 redundancy) provide sufficient energy for 8 × 400 W GPUs and 2 CPUs. The system can draw over 3.5 kW under full load. Four large fans and air shrouds maintain stable GPU temperatures. It is designed for data centers with good rack airflow and power provisioning.


Management

The integrated BMC (ASPEED AST2600) features IPMI 2.0 and remote KVM. It has a dedicated management port, plus front USB and status LEDs. It supports Supermicro SuperDoctor and Server Manager.


Chassis Design

The server has a 4U height (17.6 ″ W × 6.9 ″ H × 35.4 ″ D ≈ 900 mm depth). It features a modular two-drawer layout: the top 1U for CPUs and memory, and the bottom 3U for GPUs and the switch board. The fully equipped server weighs about 75 kg. Rack rails are included.



Performance and Typical Use: Supermicro SYS-420GP-TNAR+


This server excels in various applications:


  • AI and Deep Learning Training — It offers massive GPU performance with fast interconnect (NVSwitch).

  • HPC Workloads — Ideal for simulations, CFD, genomics, and scientific modeling.

  • Data Analytics and Research — Its large memory and NVMe storage can handle big datasets easily.

  • GPU Virtualization — The MIG feature allows for dividing GPUs for multiple users or smaller jobs.


The A100 80GB GPUs deliver up to 20 × faster training speed than previous generation models. The dual-Xeon architecture minimizes CPU bottlenecks for GPU tasks. Adding 100 GbE or InfiniBand adapters is common in multi-node clusters for faster data exchange.



Power and Cooling Requirements: Supermicro SYS-420GP-TNAR+


  • Max Load: Approximately 4 kW (when GPUs are fully active).

  • PSUs: Four 3000 W redundant (80 Plus Titanium).

  • Cooling: Front-to-back airflow with high-speed fans.

  • Environment: Designed for a data center rack with stable temperature (10–35 °C) and sufficient airflow.

  • Noise: Very loud under load – suitable for rack use only.



Upgrade and Future Options: Supermicro SYS-420GP-TNAR+


Component

Upgrade Path

CPU

All 3rd Gen Xeon Scalable CPUs (up to 40 cores / 270 W)

Memory

Up to 8 TB DDR4 or 12 TB with Optane PMem 200

Storage

6 front bays for additional NVMe/SATA/SAS drives

Networking

Supports 25 GbE / 100 GbE / InfiniBand

GPU Platform

Fixed to 8× A100 SXM4 HGX board (no GPU mixing)

Software

Certified for NVIDIA CUDA, TensorFlow, PyTorch, and major HPC frameworks


This hardware will remain relevant for several years in AI, HPC, and research applications. The A100 platform is widely used in data centers and supports modern AI frameworks.



Final Details: Supermicro SYS-420GP-TNAR+

  • Price: 55 000 EUR (EXW)

  • Condition: New

  • Warranty: 3 Years from Supermicro (official OEM warranty)

  • Availability: In Stock – Ready to Ship



Supermicro SYS-420GP-TNAR+: Only €55,000

✔️ 3-Year Warranty – No Risk: Pay Only After Testing

Comments


bottom of page