NTS Elite APEX H100 AI Training Server

MPN G242-P36
AI & HPC-ready 2U Arm server powered by Ampere Altra® Max, supporting up to 2× PCIe Gen4 GPUs for advanced AI training, inference, and high-performance computing workloads.

Key capabilities

  • Hardware-level root of trust support
  • Up to 2 x NVIDIA® H100 PCIe Gen4 GPUs
  • Up to 2 x NVIDIA® BlueField®-2 DPUs
  • Single Ampere® Altra® Max or Altra® Processors
  • 8-Channel DDR4 RDIMM/LRDIMM per CPU with 16 x DIMMs
  • 2 x 1 Gb/s LAN ports via Intel® I350-AM2
  • 4 x 2.5" Gen4 NVMe hot-swap bays
  • 2 x M.2 slots with PCIe Gen4 x4
  • 2 x FHFL PCIe Gen4 x16 slots for GPUs
  • 2 x LP PCIe Gen4 x16 slots on the rear side for DPUs
  • 2 x LP PCIe Gen4 x8 slots on the rear side
  • 1+1 1600 W 80 PLUS Platinum power supplies
Part#: APXAM012U2H1


Product
NTS Elite APEX H100 AI Training Server
Part number
G242-P36
Category
Systems › GPU Systems
Form factor
rackmount
Typical workloads
AI training, inference, and HPC
Configuration
Engineer-to-order via Configure (CPU, memory, GPU, storage, networking).
Vendor
RackmountNTS (New Tech Solutions, Inc.), Fremont, California, USA.
Facility
ISO-aligned staging, imaging, and burn-in at NTS HQ in Fremont, CA.

NTS Elite APEX GIGABYTE G242-P36 Arm-Based 2U AI/HPC Server


The NTS Elite APEX GIGABYTE G242-P36 Arm-Based 2U AI/HPC Server is designed for cloud infrastructure, edge computing, accelerated computing, artificial intelligence (AI), and high-performance computing (HPC) workloads. Powered by a single Ampere® Altra® Max or Ampere® Altra® processor, this platform combines high core counts, PCIe Gen4 connectivity, and power-efficient Arm architecture in a compact 2U rackmount design.
The G242-P36 supports up to two NVIDIA® H100 PCIe Gen4 GPUs for accelerated AI training and compute-intensive workloads, along with support for up to two NVIDIA® BlueField®-2 DPUs for advanced data processing and infrastructure acceleration. Its eight-channel DDR4 memory architecture, flexible NVMe storage, PCIe expansion, and redundant power supplies make it suitable for cloud service providers, enterprise infrastructure, and research environments.
Built around Ampere's cloud-native processor architecture, the platform is designed to deliver predictable performance, scalability, and power efficiency. Hardware-level Root of Trust, remote server management, automatic fan speed control, and power-management technologies help support secure and reliable infrastructure operations.
New Tech Solutions (RackMountNTS) offers the GIGABYTE G242-P36 as an engineer-to-order server platform. Use Configure to select supported processors, memory, accelerators, storage, networking, and other system options. NTS reviews the proposed configuration and validates power, cooling, firmware, and drivers in Fremont, California before shipment.

Key Features and Benefits


Ampere Altra Max Arm Processor Architecture


  • Supports a single Ampere® Altra® Max or Ampere® Altra® processor.
  • Designed for cloud-native infrastructure, cloud service providers, and edge computing.
  • Ampere Altra Max processor family offers configurations with up to 128 cores.
  • High core density supports multiple concurrent workloads and scalable computing environments.
  • Designed to deliver predictable performance and performance-per-watt efficiency.
  • Supports PCIe Gen4 connectivity for high-throughput GPU, storage, and networking configurations.

NVIDIA GPU Acceleration


  • Supports up to two NVIDIA® H100 PCIe Gen4 GPUs.
  • Two full-height, full-length PCIe Gen4 x16 slots are provided for GPU installation.
  • Designed for GPU-accelerated AI training, inference, and HPC applications.
  • Supports accelerated computing environments that require parallel processing and high-throughput data access.
  • The GIGABYTE qualified component information also lists an A100 PCIe GPU card; confirm the exact supported accelerator and configuration with NTS before ordering.

NVIDIA BlueField-2 DPU Support


  • Supports up to two NVIDIA® BlueField®-2 DPUs.
  • Two rear low-profile PCIe Gen4 x16 slots are provided for DPU installation.
  • Designed to support infrastructure acceleration and data-processing workloads.
  • Helps provide additional flexibility for networking and data-center infrastructure configurations.

High-Bandwidth DDR4 Memory


  • 16 DDR4 RDIMM/LRDIMM memory slots.
  • Eight-channel memory architecture per processor.
  • Supports memory speeds up to 3200 MHz.
  • Designed for memory-intensive cloud, edge, and enterprise applications.
  • Provides memory bandwidth for high-core-count Arm processor workloads.

Flexible NVMe Storage


  • Four front-accessible 2.5-inch PCIe Gen4 NVMe hot-swap drive bays.
  • Two internal M.2 slots with PCIe Gen4 x4 interfaces.
  • Tool-less drive bay design for convenient drive installation and replacement.
  • Supports enterprise-level SATA, SAS, SSD, and NVMe storage components through qualified configurations and optional controllers where applicable.
  • Optional PCIe RAID and HBA cards can be considered for supported storage configurations.

PCIe Gen4 Expansion and Networking


  • Two full-height, full-length PCIe Gen4 x16 slots for GPU accelerators.
  • Two rear low-profile PCIe Gen4 x16 slots for DPUs.
  • Two rear low-profile PCIe Gen4 x8 expansion slots.
  • Two 1Gb/s LAN ports powered by the Intel® I350-AM2 controller.
  • Optional Ethernet and InfiniBand networking cards are listed in the qualified component information.
  • Expansion flexibility for storage controllers, networking adapters, and infrastructure accelerators.

Hardware-Level Security


The GIGABYTE G242-P36 includes hardware-level Root of Trust (RoT) support to help protect the system during the boot process.
  • Hardware-level Root of Trust integrated into the platform.
  • Helps verify firmware integrity during system startup.
  • Designed to isolate and verify cryptographic operations during the boot process.
  • Helps protect against firmware compromise and unauthorized modifications.
  • Optional TPM 2.0 module support for hardware-based authentication.
  • TPM technology can securely store passwords, encryption keys, and digital certificates.

Power Efficiency and Intelligent Cooling


The platform incorporates GIGABYTE power-management and cooling technologies to help improve energy efficiency and system operation.
Automatic Fan Speed Control
  • Automatically adjusts individual fan speeds based on temperature sensor readings.
  • Helps balance system cooling requirements and power consumption.
  • Supports efficient thermal management under varying workloads.
Cold Redundancy
  • Designed for systems with N+1 redundant power supplies.
  • When total system load falls below 40%, one power supply can enter standby mode.
  • GIGABYTE states this feature can improve power efficiency by approximately 10% under the specified operating conditions.
Redundant Power Supply
  • 1+1 1600W 80 PLUS Platinum redundant power supplies.
  • Provides power redundancy for supported system configurations.

High Availability and System Protection


Smart Ride Through (SmaRT)
  • Helps protect against unexpected AC power interruptions.
  • Temporarily adjusts system power consumption to maintain availability.
  • Power-supply capacitors provide approximately 10–20 ms of support during a transition to a backup power source.
Smart Crises Management and Protection (SCMP)
  • GIGABYTE technology designed to protect supported server configurations during PSU faults or overheating events.
  • Can force the CPU into an ultra-low-power operating mode to reduce system power demand.
  • Helps reduce the risk of unexpected shutdowns, component damage, and data loss.

Remote Server Management


The integrated Baseboard Management Controller (BMC) supports remote monitoring and administration through GIGABYTE server management applications.
GIGABYTE Management Console
  • Browser-based single-server management interface.
  • Server health monitoring.
  • Remote troubleshooting.
  • Resource utilization monitoring.
  • Automatic recording functions.
  • SAS and RAID controller monitoring.
  • Integration with third-party applications.
GIGABYTE Server Management (GSM)
  • Multiple-server management platform.
  • Supports IPMI and Redfish compatibility.
  • Helps administrators monitor and manage server infrastructure across deployments.

Supported GPU and Accelerator Configurations


The GIGABYTE G242-P36 supports GPU and DPU acceleration through dedicated PCIe Gen4 expansion slots.
NVIDIA GPU configuration
  • Up to 2 × NVIDIA® H100 PCIe Gen4 GPUs.
  • GIGABYTE's qualified component information also lists an NVIDIA A100 PCIe GPU card. Confirm the supported configuration and availability before selecting this option.
NVIDIA DPU configuration
  • Up to 2 × NVIDIA® BlueField®-2 DPUs.
Expansion architecture
  • 2 × full-height, full-length PCIe Gen4 x16 GPU slots.
  • 2 × rear low-profile PCIe Gen4 x16 DPU slots.
  • 2 × rear low-profile PCIe Gen4 x8 slots.
The H100 and BlueField-2 configurations provide different types of acceleration: GPUs support parallel computing and AI workloads, while DPUs are designed for infrastructure and data-processing acceleration. Final accelerator combinations should be confirmed against platform compatibility and power requirements.

Key Applications and Use Cases


AI Training and Deep Learning

Supports GPU-accelerated AI training environments using up to two NVIDIA H100 PCIe GPUs. Suitable for deep learning development, neural network workloads, and computationally intensive AI applications.

AI Inference

Provides a platform for deploying trained AI models and running inference workloads that benefit from GPU acceleration and high-core-count Arm processors.

High-Performance Computing (HPC)

Designed for compute-intensive applications, parallel processing, research workloads, and scientific computing environments that require scalable processor and accelerator resources.

Cloud Computing and Cloud-Native Infrastructure

The Ampere Altra processor architecture is designed for cloud-native environments, offering high core counts, predictable performance, and power efficiency for cloud service providers and enterprise infrastructure.

Edge Computing

The compact 2U platform and power-efficient Arm architecture make it suitable for edge infrastructure deployments requiring compute density, accelerated processing, and flexible connectivity.

Data Center Infrastructure Acceleration

With optional NVIDIA BlueField-2 DPU support, the platform can be configured for infrastructure acceleration and data-processing workloads within supported data-center environments.

Virtualized and Containerized Workloads

The high-core-count Ampere processor architecture can support cloud-native, containerized, and consolidated infrastructure environments, subject to application and software compatibility.

Research and Scientific Computing

Supports research teams and technical environments running parallel computing, simulations, data analysis, and other compute-intensive workloads.

Software Ecosystem and Platform Compatibility


The GIGABYTE G242-P36 qualified software ecosystem information lists the following operating system versions:
  • SUSE: SLES 15 SP2, SLES 15 SP3.
  • Ubuntu: Ubuntu 18.04.5 LTS, Ubuntu 20.04.1 LTS.
  • Red Hat: RHEL 8.3, RHEL 8.5.
  • Fedora: Fedora Server 33-1.2, Fedora Server 35-1.2.
  • Debian: Debian 10.9 (Buster).
  • Oracle Linux: Oracle Linux R8 U2, Oracle Linux R8 U5.
  • CentOS: CentOS 8.3-2011, CentOS 8.4.2105, CentOS 8.5.2111.
Operating system and software compatibility should be confirmed for the intended processor, accelerator, driver, and application configuration before deployment.

NTS Engineer-to-Order Configuration and Validation

The NTS Elite APEX GIGABYTE G242-P36 Arm-Based 2U AI/HPC Server is quoted engineer-to-order by New Tech Solutions (RackMountNTS). Use Configure to select supported Ampere Altra or Altra Max processor options, memory, GPU accelerators, DPUs, storage, and networking. NTS reviews the proposed bill of materials (BOM) and validates power, cooling, firmware, and drivers in Fremont, California before systems ship.
Federal, defense, and SLED programs can align the same BOM to SEWP V, ITES-4H, GSA MAS, or applicable cooperative vehicles when the statement of work (SOW) allows. Commercial buyers receive the same configuration review, staging discipline, serial-tracked acceptance, and lifecycle support path after handoff.
Share workload requirements, target GPU or DPU counts, processor and memory requirements, Ethernet or InfiniBand fabric preferences, rack power budget, and delivery window through contact NTS or Request a Quote. NTS can provide a reviewed configuration with applicable lead times, dual-source notes when required, and a package prepared for contracting review.
From individual systems to larger infrastructure deployments, NTS helps maintain configuration consistency across processors, accelerators, storage, and networking. This engineering approach supports deployment planning and expansion without restarting the configuration process for each system.
After you select available options in Configure, pricing updates in real time. Request a Quote to receive a configuration package with applicable lead times, dual-source notes when required, and acceptance documentation aligned with your receiving process. Configurable systems remain engineer-to-order, with the same Fremont staging and validation process.
Questions about GPU compatibility, BlueField-2 DPU configurations, Ethernet or InfiniBand networking, storage expansion, rack power requirements, or contract-vehicle packaging can be discussed with an NTS specialist using your draft BOM.
NTS supports commercial, federal, defense, and SLED buyers through the same engineering process: design review, component validation, assembly, firmware and driver preparation, and ship-ready documentation from the Fremont facility.

Product overview

Highlights and workloads for NTS Elite APEX H100 AI Training Server.

Overview

AI & HPC-ready 2U Arm server powered by Ampere Altra® Max, supporting up to 2× PCIe Gen4 GPUs for advanced AI training, inference, and high-performance computing workloads.

 

Dimensions2U (W438 x H87.5 x D820 mm)
MotherboardMP32-AR2
CPUAmpere® Altra® Max or Altra® Processor
Single processor, 7nm technology, LGA4926 socket
Up to 128-core per processor
ChipsetSystem on Chip
Memory8-Channel DDR4 memory, 16 x DIMM slots
RDIMM/LRDIMM modules up to 256GB supported
Up to 4TB of memory capacity supported per processor
Memory speed: Up to 3200 MHz
NOTE: Only supports configurations with 1, 2, 4, 6, 8, 12, or 16 DIMMs
LAN2 x 1GbE LAN ports (1 x Intel® I350-AM2)
1 x 10/100/1000 management LAN
VideoIntegrated in Aspeed® AST2500
2D Video Graphic Adapter with PCIe bus interface
1920x1200@60Hz 32bpp, DDR4 SDRAM
Storage4 x 3.5" Gen4 NVMe hot-swappable bays
- 2.5" Gen4 NVMe SSD supported only
SASN/A
RAIDN/A
Expansion Slots4 x PCIe 4.0 x16 slots, optional NVIDIA A100 GPU
2 x PCIe 4.0 x16 slots, optional NVIDIA BlueField-2 DPU
2 x PCIe 4.0 x8 slots, low-profile
2 x M.2 slots (4.0 x4), supports 2242/2260/2280/22110 cards
Front I/O1 x USB 3.2 Gen1
Rear I/O3 x USB 3.2 Gen1, 1 x VGA, 1 x COM port, 2 x RJ45, 1 x MLAN
Backplane I/OBackplane P/N: 9CBP1047NR-00
Speed and bandwidth: Gen4 NVMe
TPM1 x TPM header with SPI interface
Optional TPM2.0 kit: CTM010
Power SupplyDual 1600W 80 PLUS Platinum power supply
AC input: 100-240V
System ManagementAspeed® AST2500 management controller
GIGABYTE Management Console (AMI MegaRAC SP-X)
OS CompatibilityRHEL 8.3 / 8.5 (ARM64)
SLES 15 SP2 / 15 SP3 (ARM64)
Ubuntu 18.04.5 LTS / 20.04.1 LTS / 22.04 LTS (ARM64)
Fedora Server 33-1.2 / 35-1.2 (ARM64)
OracleLinux R8 U2 / R8 U5 (ARM64)
Debian 10.9 (Buster) / 11.1 (ARM64)
System Fans5 x 80x80x38mm (16,300rpm)
Operating PropertiesOperating temperature: 10°C to 35°C
Operating humidity: 8-80% (non-condensing)
Non-operating temperature: -40°C to 60°C
Non-operating humidity: 20%-95% (non-condensing)
Packaging Content1 x G242-P36 system
1 x CPU heatsink
1 x Rail kit
Reference NumbersBarebone with rail kit: G242P36MB-00
- Motherboard: MP32-AR2NR-00
- Rail kit: 25HB-3A020-C0R
- CPU heatsink: 25ST1-253420-C1R
- Back plane board: 4_port: 9CBP1047NR-00
- PCIe Riser Card_2-port NVMe: 9CNG3132NR-00
- Power supply: 25EPO-216008-LOS

 

Build Your Configuration

Processors · memory · storage · networking · power
Select options below — pricing updates in real time as you configure.
  • Real-time pricing
  • SEWP V · ITES-4H quoting
  • U.S. integration & burn-in

Expand each group below to choose options — required fields are marked. Selections update pricing in real time.

Barebone
Processor
Memory
M.2 DRIVE
(Max Quantity: 2)
GPU
(Max Quantity: 2)
CONTROLLER CARD
Battery Backup
NETWORK ADAPTER
(Max Quantity: 4)
Trusted Platform Module
Power Cables
OPERATING SYSTEM
NTS AI Stack See what's inside each NTS AI package
Software
Warranty

Why teams choose NTS

Engineer-to-order platforms with U.S. integration, federal contract paths, and workload-aware BOM review — not catalog-only SKUs.

Enterprise GPU rack servers staged for engineer-to-order deployment

Built in the USA

Configuration, burn-in, and rack staging from Fremont, California with nationwide delivery.

Contract-native quoting

ITES-4H, SEWP V, and OMNIA Partners paths with CLIN-ready BOM structure.

Engineer-to-order

Choose CPU, memory, up to 4 gpus, storage, network, and redundant power per workload.

Rack-ready delivery

Serial capture for CMDB, integration validation, and specialist turn-up support.

Solutions & Deployment

Optimized reference architectures, workload deployment patterns, and technical specifications for the NTS Elite APEX H100 AI Training Server

Platform at a Glance

Rackmount server chassis staged for factory burn-in and rack-ready deployment

Rackmount Chassis

Custom engineer-to-order rackmount chassis featuring rigorous factory burn-in, thermal validation, and seamless rack-ready deployment.
Enterprise server PCIe expansion with NICs, HBAs, and accelerator cards

Enterprise Expansion

High-bandwidth PCIe Gen 4/5 expansion slots supporting high-speed NICs, SAS/SATA/NVMe HBAs, and dedicated hardware accelerators.
U.S. integration facility validating server systems for federal and SLED programs

U.S. Integration

Secure U.S.-based configuration, multi-point validation, and compliant logistics tailored for federal, defense, and SLED programs.
Procurement specialist preparing federal and SLED contract quotes

Contract Quoting

Streamlined procurement via ITES-4H, NASA SEWP V, and SLED cooperative contracts with pre-negotiated pricing.

Delivery & Integration Lifecycle

From initial BOM design to production-ready deployment, our dedicated engineering team manages the complete lifecycle of your NTS Elite APEX H100 AI Training Server.
NTS engineers staging server racks with structured cabling before datacenter deployment
  • Build & Burn-In
    Precision factory assembly, custom firmware baselining, rigorous stress testing, and comprehensive asset documentation prior to shipment.
  • Rack Integration
    Structured cabling, optimized power distribution, and comprehensive in-rack validation aligned with your specific data center standards.
  • Image & Tag
    Custom OS/hypervisor imaging, host-name provisioning, and automated serial/asset tag capture for seamless CMDB and ITAM integration.
  • Deliver & Support
    Secure, coordinated logistics combined with post-delivery engineering support to ensure rapid, hassle-free site turn-up.
  • GPU Readiness
    Cluster networking checks and workload smoke tests before handoff.
GPU server architecture with accelerators, host compute, and high-speed I/O

System Architecture

NTS Elite APEX H100 AI Training Server is engineer-to-order for GPU Systems workloads — built for sustained accelerator duty cycles, in-rack serviceability, and network fabric headroom as your cluster scales.
  • Right-size CPU, memory, and I/O in an engineer-to-order BOM — validated and burn-tested in Fremont before ship
  • Add NICs, HBAs, and accelerators through PCIe expansion without chassis constraints
  • Scale NVIDIA HGX-class multi-GPU topologies with fabric-ready host I/O
  • Scale east-west and cluster traffic on 10/25/100GbE-class networking without platform upgrades
  • Match storage latency to workload — NVMe, SAS, or SATA tiers in the same chassis
  • Keep mission workloads online with redundant power and cooling for 24×7 operation
  • Image, monitor, and troubleshoot remotely from day one via IPMI / BMC
Federal procurement specialist reviewing contract compliance documentation alongside secure server integration

Procurement & Compliance

Procure NTS Elite APEX H100 AI Training Server through SEWP V, ITES-4H, and SLED cooperative contracts. Benefit from CLIN-ready BOM structures, full compliance documentation, and secure delivery coordinated by our Fremont integration specialists.
  • Acquire federal, DoD, and public-sector quotes precisely mapped to your contract CLINs, funding cycles, and periods of performance
  • Access complete Trade Agreements Act (TAA) compliance and country-of-origin documentation for seamless contracting officer approval
  • Streamline agency acquisition reviews with detailed Energy Star ratings and power-efficiency metrics
  • Maintain strict property accountability with pre-captured serial numbers, MAC addresses, and custom asset tags for audit-ready tracking
  • Ensure compliance with FIPS 140-3 and NIST SP 800-53 security standards through pre-award engineering consultations
  • Coordinate secure, scheduled delivery windows directly with your ACO or COR, arriving fully integrated and rack-ready
SEWP V ITES-4H SLED Cooperatives CLIN-ready BOM Fremont, CA
Contract vehicles for this SKU are listed under Available through next to the product image. Explore SEWP V, ITES-4H, GSA, and SLED procurement paths →

Ideal Use Cases

Enterprise deployment scenarios where NTS Elite APEX H100 AI Training Server delivers optimal price-performance, high reliability, and simplified serviceability.
GPU cluster training large language models at scale in an NTS data center

LLM Training

Fine-tune and train large language models at scale.
Multi-GPU HGX server tray for deep learning training on NTS hardware

Deep Learning

Multi-GPU training for CV, NLP, and GenAI workloads.
High-density HPC compute cluster running scientific simulations on NTS systems

HPC Simulations

Scientific computing and high-density parallel jobs.
NTS GPU server delivering real-time AI inference and batch processing

AI Inference

Real-time inference and batch data processing.
Computer vision lab training and deploying models on NTS GPU servers

Computer Vision

Training and deployment for vision pipelines.
NTS GPU rack powering generative AI, diffusion, LLM serving and RAG infrastructure

Generative AI

Diffusion, LLM serving, and RAG infrastructure.

Common workload profiles

Typical deployment patterns aligned to NTS Elite APEX H100 AI Training Server capacity, I/O profile, and service tiers.
Multi-node HGX GPU cluster with high-bandwidth fabric and NTS branding for distributed training

Distributed training

Multi-node gradient sync across high-bandwidth GPU fabric.
Open GPU tray and dataset staging with NTS plaque for foundation model fine-tuning

Model fine-tuning

Adapt foundation models on domain-specific datasets.
Dense GPU inference rack with NVMe scratch and NTS branding for batch scoring

Batch inference

High-throughput scoring with optimized batch sizing.
GPU server beside flash array for vector search and embedding retrieval on NTS hardware

Vector search

Embedding indexes and similarity retrieval at scale.
Hybrid HPC and AI GPU chassis with NTS plaque for coupled simulation pipelines

Simulation + AI

Coupled HPC solvers with GPU-accelerated pipelines.
GPU render farm nodes with fast scratch I/O and NTS branding for frame batching

Render farms

Frame batching with fast scratch and asset I/O.

Frequently Asked Questions

Common technical and procurement topics for NTS Elite APEX H100 AI Training Server. Additional questions are handled by our specialists and knowledge base.

Need architecture guidance or a formal quote?

Service & Trust

Coverage, procurement, and domain expertise for AI Solutions platforms — backed by U.S. integration and contract-native quoting.
  • NTS Fremont integration floor — rack staging and burn-in with NTS branding on the rack
    Built & Supported in the USA Factory-aligned configuration, validation, burn-in, and rack integration from Fremont, CA — with nationwide logistics for federal and commercial programs.
  • Nationwide U.S. logistics and data center delivery support with NTS-branded equipment crates
    Nationwide Coverage Delivery and post-sales engineering across all U.S. regions — defense, civilian agency, higher education, and commercial data center.
  • Contract-native quoting workstation with CLIN-aligned BOMs beside an NTS-branded secure server
    Contract-Native Quoting CLIN-aligned BOMs for ITES-4H, SEWP V, and SLED cooperative vehicles — view all contract paths.
  • NTS solution architects consulting on an AI and HPC rack with NTS branding on the chassis
    AI Solutions Expertise Dedicated solution architects for AI, HPC, virtualization, storage, and edge — from first quote through rack turn-up.