Gigabyte G593-ZD1-AAX3 8SFF/NVMe
- Condition
- New
- Manufacturer
- GIGABYTE
- RAM
- 6144GB (DDR5 ECC REG)
- NIC card
- 2x 10GbE (Intel X710-AT2)
- GPU
- 8 x NVIDIA H200
- Accelerator manufacturer
- NVIDIA
- Accelerator model
- NVIDIA H200 (HGX H200)
- Installed GPU/APU count
- 8 GPUs
- Maximum GPU/APU count
- 8 SXM GPUs
- Memory per accelerator
- 141GB
- Total accelerator memory
- 1128GB
- GPU memory type
- HBM3e
- Accelerator memory bandwidth
- 4.8TB/s per GPU
- Accelerator form factor
- SXM
- Accelerator interconnect
- Fourth-generation NVIDIA NVLink with NVSwitch
- Accelerator-to-CPU interface
- PCIe 5.0 x16 per GPU through the HGX baseboard
- Supported compute data types
- FP64, FP32, TF32, BF16, FP16, FP8, INT8
- Accelerator virtualization
- NVIDIA vGPU, SR-IOV and GPU passthrough
- MIG support
- Up to 7 isolated GPU instances per GPU
- Software ecosystem
- NVIDIA CUDA, NVIDIA AI Enterprise and NVIDIA Transformer Engine
- Maximum system power
- 18kW
- Cooling
- Air cooling with passive SXM accelerator modules and a dedicated GPU-tray fan array
- Recommended workloads
- Large-model AI training, fine-tuning and inference, LLM and NLP workloads, HPC, simulation, analytics and data science
- Dimensions
- 219.7 x 447 x 945 mm (H x W x D)
- Weight
- 91 kg
Need a technical consultation on choosing a server?
Submit a requestGigabyte G593-ZD1-AAX3 8SFF/NVMe is a 5U enterprise GPU server storage configuration with 8 front-accessible 2.5-inch hot-swap bays for PCIe Gen5 NVMe, SATA or SAS-4 drives. It is designed for AI factories, research centers, cloud providers and enterprise data centers that need fast local storage for accelerated workloads.
Key features:
-
Storage basket and service access: The chassis provides 8 front-accessible 2.5-inch PCIe Gen5 NVMe, SATA or SAS-4 hot-swap positions. Supported drives can be serviced without opening the chassis, helping reduce planned maintenance time.
-
Accelerator subsystem: The installed accelerator subsystem contains 8 x NVIDIA H200 SXM 141GB (HGX H200), providing 1,128GB (8 x 141GB) of aggregate GPU memory. Fourth-generation NVIDIA NVLink with NVSwitch; 900 GB/s per GPU.
-
Storage topology and data path: Each front position supports PCIe Gen5 x4 NVMe, SATA 6Gb/s or SAS-4 24Gb/s connectivity. A compatible storage controller is required for SATA and SAS drives. Two internal M.2 slots provide PCIe Gen3 x4 and x1 connectivity.
-
Enterprise compute platform: The dual-socket platform supports AMD EPYC 9005 or 9004 series processors and is configured with 6,144GB DDR5 ECC registered memory across 24 DIMM slots. It supplies CPU, memory and PCIe resources for the accelerator complex and production services.
-
Management and availability: ASPEED AST2600 BMC, dedicated management LAN, GIGABYTE Management Console and 2 x 10GbE Intel X710-AT2; 5+1 x 3000W 80 PLUS Titanium redundant power supplies. These facilities support remote administration, health monitoring and resilient operation.
Use cases:
-
AI model training and fine-tuning: Uses the installed NVIDIA H200 SXM 141GB (HGX H200) subsystem for training, fine-tuning and large-model development.
-
Inference and production AI services: Provides parallel compute and accelerator memory for LLM, multimodal and enterprise inference services.
-
HPC, simulation and analytics: Accelerates scientific computing, numerical simulation, analytics and other parallel workloads supported by NVIDIA H200 SXM 141GB (HGX H200).
-
Data-intensive pipelines: Combines 8 front 2.5-inch multi-protocol positions with high-bandwidth GPU and network paths for datasets, checkpoints, staging and local scratch storage.
Gigabyte G593-ZD1-AAX3 8SFF/NVMe is a purpose-built 5U GPU platform for organizations that need 8 front 2.5-inch hot-swap bays for NVMe, SATA or SAS-4 drives, 1,128GB (8 x 141GB) of installed GPU memory and enterprise-class compute and management in one deployable system.
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.