1/2

NVIDIA HGX B300

GIGAPOD AI DLC Rack Scale Solution

Built on the NVIDIA HGX B300 platform
8 x GIGABYTE G4L4 / G4L3 4U DLC GPU servers
64 x NVIDIA Blackwell Ultra GPUs
16 x AMD EPYC^™ 9005/9004 Series Processors or
Intel^® Xeon^® 6700/6500-Series Processors
2.1 TB HBM3E GPU memory per server
Up to 109 kW rack power consumption
Reserved space for InfiniBand / Ethernet switches
Integrated G-REX cluster-level DLC power and cooling management kit
Compatible with GIGABYTE POD Manager software for cluster management / orchestration
Supports flexible storage with GIGABYTE storage servers and validated partner solutions

儲存

	DL83-GP6
Cooling Type	Direct Liquid Cooling
Rack Height	42U
Server Model	G4L4-SD3-LAX7	G4L4-ZD3-LAX7
Server Configuration	8 x 4U DLC GPU servers
CPU	Intel^® Xeon^® 6 Processors - Intel^® Xeon^® 6700-Series Processors - Intel^® Xeon^® 6500-Series Processors Total 16 processors	AMD EPYC^™ 9005 Series Processors AMD EPYC^™ 9004 Series Processors Total 16 processors
GPU	NVIDIA HGX B300 - Total 64 x NVIDIA Blackwell Ultra SXM
Switch	Flexible validated InfiniBand / Ethernet switch configurations
PDU	6 x PDUs Input: 415 V, 100 A, 3-phase
Rack Power Consumption	Up to 109 kW
CDU	In-Rack Liquid-to-Liquid CDU Cooling Capacity: 200 kW (4°C approach temperature) Primary Loop Connections: 1" FD83 QDC couplings (inlet/outlet) Input Power: 2 x C20, AC 100-240V , 50/60 Hz 1+1 redundant power supplies and pumps
Management	Integrated G-REX DLC power and cooling management kit: - 1 x N120-LS0 management node - Real-time cluster-level monitoring and control - Supports Modbus, Redfish, and REST APIs for seamless integration with CDUs and RDHx Optional GIGABYTE POD Management (GPM) software suite: - Essential single-node BMC for real-time hardware health and remote system oversight - Unified cluster-scale management and deep telemetry for high-density deployments - Total POD-level orchestration for infrastructure provisioning and environmental monitoring
Storage Solutions	Flexible validated partner solutions with GIGABYTE storage servers

DL83-GP6
Direct Liquid Cooling
42U
G4L4-SD3-LAX7
8 x 4U DLC GPU servers
Intel^® Xeon^® 6 Processors - Intel^® Xeon^® 6700-Series Processors - Intel^® Xeon^® 6500-Series Processors Total 16 processors
NVIDIA HGX B300 - Total 64 x NVIDIA Blackwell Ultra SXM
Flexible validated InfiniBand / Ethernet switch configurations
6 x PDUs Input: 415 V, 100 A, 3-phase
Up to 109 kW
In-Rack Liquid-to-Liquid CDU Cooling Capacity: 200 kW (4°C approach temperature) Primary Loop Connections: 1" FD83 QDC couplings (inlet/outlet) Input Power: 2 x C20, AC 100-240V , 50/60 Hz 1+1 redundant power supplies and pumps
Integrated G-REX DLC power and cooling management kit: - 1 x N120-LS0 management node - Real-time cluster-level monitoring and control - Supports Modbus, Redfish, and REST APIs for seamless integration with CDUs and RDHx Optional GIGABYTE POD Management (GPM) software suite: - Essential single-node BMC for real-time hardware health and remote system oversight - Unified cluster-scale management and deep telemetry for high-density deployments - Total POD-level orchestration for infrastructure provisioning and environmental monitoring
Flexible validated partner solutions with GIGABYTE storage servers

DL83-GP6
Direct Liquid Cooling
42U
G4L4-ZD3-LAX7
8 x 4U DLC GPU servers
AMD EPYC^™ 9005 Series Processors AMD EPYC^™ 9004 Series Processors Total 16 processors
NVIDIA HGX B300 - Total 64 x NVIDIA Blackwell Ultra SXM
Flexible validated InfiniBand / Ethernet switch configurations
6 x PDUs Input: 415 V, 100 A, 3-phase
Up to 109 kW
In-Rack Liquid-to-Liquid CDU Cooling Capacity: 200 kW (4°C approach temperature) Primary Loop Connections: 1" FD83 QDC couplings (inlet/outlet) Input Power: 2 x C20, AC 100-240V , 50/60 Hz 1+1 redundant power supplies and pumps
Integrated G-REX DLC power and cooling management kit: - 1 x N120-LS0 management node - Real-time cluster-level monitoring and control - Supports Modbus, Redfish, and REST APIs for seamless integration with CDUs and RDHx Optional GIGABYTE POD Management (GPM) software suite: - Essential single-node BMC for real-time hardware health and remote system oversight - Unified cluster-scale management and deep telemetry for high-density deployments - Total POD-level orchestration for infrastructure provisioning and environmental monitoring
Flexible validated partner solutions with GIGABYTE storage servers

[#1] 本網站所提供之產品規格、圖片及其他資訊僅供參考，如有差異應以實際產品為準。技嘉科技保留隨時修改內容的權利，並不對因使用上述資料而導致的任何損失承擔責任。

[#2] 本產品所標示之效能數據為晶片廠商或相關介面標準制定組織所公佈的最大理論值，實際效能可能因系統配置及使用環境而有所不同。

[#3] 本文所使用的所有商標及企業識別標誌均為其合法所有者的財產。