Skip to main content
Out of stock
  • $48,000.00
  • Free 76-day Returns
Sold by Newegg

Shipped by Newegg

Price alert
Shop it at NeweggBusiness.

Supermicro GPU ARS-111GL-NHR, NVIDIA GH200 Grace Hopper Superchip system supporting NVIDIA BlueField-3 or NVIDIA ConnectX-7

  • This system currently supports two E1.S drives direct to the processor and the onboard GPU only. Please consult your Supermicro Salesperson for details.
  • High density 1U GPU system with Integrated NVIDIA® H100 GPU
  • NVIDIA Grace Hopper™ Superchip (Grace CPU and H100 GPU)
  • NVLink® Chip-2-Chip (C2C) high-bandwidth, low-latency interconnect between CPU and GPU at 900GB/s
  • Up to 576GB of coherent memory per node including 480GB LPDDR5X and 96GB of HBM3 for LLM applications
  • 2x PCIe 5.0 x16 slots supporting NVIDIA BlueField®-3 or ConnectX®-7
  • 9 Hot-Swap Heavy Duty Fans with Optimal Fan Speed Control
  • This system supports two E1.S drives directly from the processor only.
+
+
Reviews
See all Q & A

Any questions? Ask CelesteSM will help you find out quickly.

There are no reviews yet.

Do you own this product?

Warranty & Returns

Warranty, Returns, And Additional Information

Warranty

  • Limited Warranty period (parts): 1 year
  • Limited Warranty period (labor): 3 years
  • Read full details

Return Policies

    We want to ensure your holiday shopping this year is hassle-free. That’s why we’re automatically extending our return policies on almost every product! For purchases placed between November 1st, 2026 and December 31, 2026 you will have until January 31, 2027 to return your product.

  • Return for refund until: January 31, 2027
  • Return for replacement until: January 31, 2027
  • This item is covered by Newegg.com's Extended Holiday Return Policy.
  • Read full return policy for details.
LOADING...

The Supermicro ARS-111GL-NHR is a 1U GPU server system built around the NVIDIA GH200 Grace Hopper Superchip, suited to data-center teams running AI and large language model workloads that benefit from a Grace CPU and H100 GPU with up to 576GB of coherent memory.

Recommended For

  • AI teams running LLM inference or fine-tuning with models or context windows that exceed GPU memory alone, and whose software can use Grace Hopper’s shared CPU–GPU memory.
  • HPC and scientific-computing teams that need a tightly coupled Arm CPU and H100 GPU for workloads that benefit from high-bandwidth CPU–GPU data sharing.
  • Data-center operators deploying a compact, single-GH200 AI node in a rack environment with the power, cooling, and Arm-platform expertise to operate it.
  • AI infrastructure teams whose deployment benefits from adding a BlueField-3 or ConnectX-7 adapter in one of the system’s PCIe slots.

Spec Summary

AttributeValue
Best ForServer barebones deployments built around the NVIDIA GH200 Grace Hopper platform, with support for NVIDIA BlueField-3 or ConnectX-7