MGX
Chenbro MGX Series Overview
The MGX modular server architecture, developed by NVIDIA, is designed to accelerate AI and HPC advancements. As an NVIDIA partner, Chenbro is dedicated to promoting the adoption and expansion of the MGX architecture by offering versatile server chassis solutions. Chenbro collaborates with system integrators and server brands to develop customized solutions, ranging from open chassis, to JDM/ODM and OEM plus services. Whether for standardized deployments or fully customized server designs, Chenbro ensures each customer receives solutions tailored to market demands, supporting diverse deployments in AI, HPC, and big data.
Key Benefits:
- Accelerated Time-to-Market: Modular architecture allows OEMs and ODMs to develop and deploy solutions faster.
- Broad Compatibility: Supports NVIDIA Grace™ CPUs, x86 architectures, and the full range of NVIDIA GPUs, including H100, L40, and more.
- Optimal TCO: Reduces development costs and ensures investment longevity with forward compatibility.
- High Flexibility: Compatible with both enterprise and cloud data centers, with configurations that suit various power, thermal, and mechanical requirements.
- Explore the NVIDIA MGX Series to unlock the full potential of accelerated computing in your data center.
Application
The MGX platform is versatile and can be used in a variety of advanced computing scenarios:
- AI and Machine Learning: Supports large-scale model training and inference with optimized power and thermal management.
- High-Performance Computing (HPC): Delivers robust performance for research and scientific computing applications.
- Digital Twins: Powers real-time simulation and visualization applications, making it ideal for smart cities and digital factories.
- Cloud Services: Flexible configurations enable the deployment of efficient cloud computing solutions for various enterprise needs.
- 5G and Edge Computing: Provides powerful and scalable infrastructure for edge AI and network processing applications.
How MGX Is Being Used
Digital Twins
HPC and Data Analytics
AI
Cloud Services
Cloud Gaming
5GChenbro MGX Solution
MGX 1U Compute Tray for NVIDIA GB200 NVL72
The MGX 1U compute tray is a server chassis designed explicitly for the GB200 NVL72. The GB200 NVL72 is poised to revolutionize AI by creating a powerful AI factory for the new industrial era. It contains 18 compute trays and houses 36 NVIDIA Grace™ CPUs and 72 NVIDIA Blackwell GPUs. The chassis design supports blind-mate liquid-cooled, accommodating 2 GB200 Superchips per chassis, ensuring efficient and scalable supercomputing performance.
Features:
• Chassis accommodates with 2x GB200 Superchips.
• Chassis design for blind-mate liquid-cooled.
• Design for supercomputing GB200 NVL72 - 18 compute trays in a rack with 36 NVIDIA Grace™ CPUs and 72 NVIDIA Blackwell GPUs.
• GB200 NVL72 server rack solution can build an AI factory for the new industrial revolution.
Launch Date: Q3 2025
For more details, download the MGX 1U Compute Tray Datasheet.
MGX 2U Compute Tray for NVIDIA GB200 NVL36
The MGX 2U compute tray is a server chassis explicitly designed for the GB200 NVL36. The GB200 NVL36 is poised to revolutionize AI by creating a powerful AI factory for the new industrial era. It has 9 compute trays and houses 18 NVIDIA Grace™ CPUs and 36 NVIDIA Blackwell GPUs. The chassis design supports blind-mate liquid-cooled, accommodating 2 GB200 Superchips per chassis, ensuring efficient and scalable supercomputing performance.
Features:
• Chassis accommodates with 2x GB200 Superchips.
• Chassis accommodates with 2x GB200 Superchips.
• Chassis design for blind-mate liquid-cooled.
• Design for supercomputing GB200 NVL36 - 9 compute trays in a rack with 18 NVIDIA Grace™ CPUs and 36 NVIDIA Blackwell GPUs.
• GB200 NVL36 server rack solution can build an AI factory for the new industrial revolution.
Launch Date: Q3 2025
For more details, download the MGX 2U Compute Tray Datasheet.
MGX 2U AI Server Chassis
Focused on AI server applications, Chenbro’s 2U enterprise-grade server chassis solutions are built on the MGX system. Their modular design and future-proof expandability support GPU, DPU, and CPU upgrades, allowing subsystem reuse across various applications and generations.
Features:
• Designed to fit standard EIA 19-inch racks, the 2U MGX chassis supports traditional PCIe GPU cards, with configurations accommodating up to four GPU cards and air-cooled solutions.
• With modular bays of varying sizes, the chassis enables users to customize accelerated computing servers to meet specific application needs.
• It features flexible configuration and future-proof compatibility for customizing enterprise-grade server chassis solutions.
MGX 4U Air-Cooled Server Chassis
Developed in collaboration with NVIDIA, Chenbro’s MGX 4U air-cooled server chassis solution is designed for AI training and HPC applications. It supports up to eight GPGPUs or GPUs, and features five front-mounted and five mid-mounted 80x80 fans brackets for efficient cooling.
Features:
• Supports up to eight air-cooled GPUs for AI training and HPC applications.
• Features five front-mounted and five mid-mounted 80x80 fans brackets for efficient cooling.
• Adopts a traditional Intel and AMD x86 CPU architecture, targeting enterprise data center demand.
• Features modular bay design for the compute tray, allowing flexible adaptation to diverse user I/O requirements.
• Compatible with standard EIA 19-inch racks.
Launch Date: Q3 2025
For more details, download the MGX 4U Air-Cooled Server Chassis Datasheet.
MGX 4U Liquid-Cooled Server Chassis
Collaborated with NVIDIA, Chenbro provides MGX 4U liquid-cooled server chassis solution designed for AI training and HPC applications. It supports up to 16 single-slot GPUs, and features liquid-cooled architecture for businesses demanding superior performance and scalability.
Features:
• Supports up to 16 liquid-cooled single-slot GPUs for AI training and HPC applications, ensuring optimal thermal efficiency for high-intensity workloads.
• The liquid-cooled architecture distributes the coolant to the GPU card assembly, motherboard, and switchboard tray by internal manifold, enhancing energy efficiency for high-performance data centers.
• Features 9 back-mounted fan brackets for efficient cooling.
• Compatible with 12 redundant CRPS PSU modules and MGX standard racks.
Launch Date: Q3 2025
For more details, download the MGX 4U Liquid-Cooled Server Chassis Datasheet.
Download
Event
Three Major Service Models
Contact Us
Please fill in your contact information in the form below and we will respond to your inquiries or questions as soon as possible.
Fill Form