Supermicro ARS-111GL-SHR 8NVMe
- Condition
- New
- Manufacturer
- Supermicro
- Form factor
- 1U
- RAM
- 480GB (LPDDR5x)
- GPU
- 1 x NVIDIA GH200 (Hopper)
- Accelerator manufacturer
- NVIDIA
- Accelerator model
- NVIDIA GH200
- Installed GPU/APU count
- 1 onboard GPU
- Maximum GPU/APU count
- 1 onboard GPU
- Memory per accelerator
- 96GB
- Total accelerator memory
- 96GB
- GPU memory type
- HBM3
- Accelerator memory bandwidth
- Up to 4 TB/s
- Accelerator form factor
- Onboard GPU integrated in the NVIDIA GH200 Grace Hopper Superchip
- Accelerator interconnect
- Not applicable (single onboard GPU)
- Accelerator-to-CPU interface
- NVIDIA NVLink-C2C, up to 900 GB/s
- Supported compute data types
- FP64, FP32, TF32, BF16, FP16, FP8, INT8
- Accelerator virtualization
- NVIDIA MIG, GPU passthrough
- MIG support
- Up to 7 isolated GPU instances
- Software ecosystem
- NVIDIA CUDA; NVIDIA AI Enterprise-compatible
- Maximum system power
- 2kW
- Cooling
- Air cooling with up to 9 removable heavy-duty 40 mm fans
- Recommended workloads
- HPC, AI and deep learning training and inference, large language models and generative AI
- Dimensions
- 43.6 x 438.4 x 900 mm (H x W x D)
- Weight
- 15.35 kg
Need a technical consultation on choosing a server?
Submit a requestSupermicro ARS-111GL-SHR 8NVMe is a 1U enterprise server storage configuration with eight front hot-swap E1.S NVMe bays. It is designed for AI factories, research centers, cloud providers and enterprise data centers that need fast local storage for AI and HPC workloads.
Key features:
-
Storage basket and service access: The selected storage basket comprises eight front hot-swap E1.S NVMe bays. Supported hot-swap drives can be serviced from the front without opening the chassis, helping reduce planned maintenance time.
-
Installed accelerator subsystem: The installed accelerator subsystem contains 1 x NVIDIA GH200 Grace Hopper Superchip. It provides 96GB HBM3 GPU memory. NVIDIA NVLink-C2C provides a 900GB/s coherent link between the Grace CPU and Hopper GPU.
-
Storage topology and data path: All eight E1.S positions support front hot-swap NVMe service. Two internal M.2 NVMe slots can be used for boot or service storage without consuming the front data bays.
-
Enterprise compute platform: The installed compute subsystem combines one 72-core NVIDIA Grace CPU with 480GB of ECC LPDDR5X memory. It supplies the CPU, memory and PCIe resources required to feed the accelerator subsystem and host production services.
-
Management and availability: BMC health monitoring and a dedicated 1GbE management port, together with 2 x 2000W redundant 80 PLUS Titanium power supplies, support remote administration, component monitoring, planned service operations and resilient data-center operation.
Use cases:
-
AI model development: Uses the installed NVIDIA GH200 Grace Hopper Superchip subsystem for model development, training and fine-tuning workloads suited to the accelerator architecture.
-
Inference and production services: Provides parallel compute and accelerator memory for LLM, multimodal and enterprise inference services.
-
HPC, simulation and analytics: Accelerates scientific computing, numerical simulation, engineering, analytics and other parallel workloads supported by the installed accelerator subsystem.
-
Data-intensive pipelines: Combines the specified 8NVMe storage basket with high-bandwidth accelerator and network paths for datasets, checkpoints, staging and local scratch storage.
Supermicro ARS-111GL-SHR 8NVMe is a precisely defined 8NVMe storage configuration for organizations that need this drive basket, installed NVIDIA GH200 Grace Hopper Superchip acceleration and dependable enterprise lifecycle management.
to Buy a Server
from Servermall
warranty
testing
We want to make sure that our equipment is fully reliable for you. That’s why all our equipment (even new) is subject to complete diagnostics, testing, and part replacement.
testing
We fully load our equipment with various utilities and software. Rest assured, it’ll work for a very long time.
Power supply
The components work at full capacity and are tested for several days. If we are not sure about something, we replace it.
of all equipment
Our regulations imply the same testing for both used and new equipment. Oh, and by the way, we complement the official manufacturer’s warranty with our own warranty.