AS-8126GS-TNMR

DP AMD 8U Server with AMD Instinct™ MI325X 8-GPU

Anewtech-Systems-GPU-Server-Supermicro-AS-8126GS-TNMR
  • Dual Socket SP5 AMD EPYC™ 9005/9004 Series Processors up to 500W with air cooling
  • 8 onboard OAM GPU accelerator cards
  • Up to 24 DIMMs supporting up to 9TB DDR5-6000 in 1DPC
  • Up to 8 PCIe 5.0 x16 LP + 2 PCIe 5.0 x16 FHFL slots
  • 8 front hot-swap 2.5" NVMe + 2 front hot-swap 2.5" SATA w/ optional 8 E1.S drives

Key Applications

  • High Performance Computing
  • AI/Deep Learning Training
  • Industrial Automation, Retail
  • Climate and Weather Modeling
Product Specification
Anewtech-Systems-GPU-Server-Supermicro-AS-8126GS-TNMR-AMD-GPU-Servers-AI-Servers-Supermicro
Anewtech-Systems-GPU-Server-Supermicro-AS-8126GS-TNMR-AMD-GPU-Servers-AI-Servers
Product SKUsA+ Server AS -8126GS-TNMR
MotherboardSuper H14DSG-OD
Processor
CPUDual processor(s)
AMD EPYC™ 9005/9004 Series Processors
NoteSupports up to 500W TDP CPUs
GPU
Max GPU CountUp to 8 onboard GPUs
Supported GPUAMD: Instinct MI300X Accelerators
CPU-GPU InterconnectPCIe 5.0 x16 CPU-to-GPU Interconnect
GPU-GPU InterconnectAMD Infinity Fabric™ Link
System Memory
MemorySlot Count: 24 DIMM slots
Max Memory (1DPC): Up to 9TB 6000MT/s ECC DDR5 RDIMM
On-Board Devices
ChipsetSystem on Chip
Input / Output
Video1 VGA port
System BIOS
BIOS TypeAMI 64MB SPI Flash EEPROM
Management
SoftwareSuperCloud Composer
Supermicro Server Manager (SSM)
Supermicro Update Manager (SUM)
Supermicro SuperDoctor® 5 (SD5)
Super Diagnostics Offline (SDO)
Supermicro Thin-Agent Service (TAS)
SuperServer Automation Assistant (SAA) New!
Power configurationsPower-on mode for AC power recovery
ACPI Power Management
Security
HardwareTrusted Platform Module (TPM) 2.0
Silicon Root of Trust (RoT) – NIST 800-193 Compliant
FeaturesCryptographically Signed Firmware
Secure Boot
Secure Firmware Updates
Automatic Firmware Recovery
Supply Chain Security: Remote Attestation
Runtime BMC Protections
System Lockdown
PC Health Monitoring
CPUMonitors for CPU Cores, Chipset Voltages, Memory
7 +1 Phase-switching voltage regulator
FANFans with tachometer monitoring
Status monitor for speed control
TemperatureMonitoring for CPU and chassis environment
Thermal Control for fan connectors
Chassis
Form Factor8U Rackmount
ModelCSE-GP805TS-R000NPF
Dimensions and Weight
Height13.8" (356 mm)
Width17.6" (447 mm)
Depth33.2" (843 mm)
Package27.6" (H) x 51" (W) x 29.5" (D)
WeightGross Weight: 158.73 lbs (72 kg)
Net Weight: 105.82 lbs (48 kg)
Available ColorSilver
Front Panel
LEDHDD activity
Network activity LEDs
System information (overheat/UID) 
UID
ButtonsPower On/Off 
UID/ Reset button
Expansion Slots
PCI-Express (PCIe) ConfigurationDefault

8 PCIe 5.0 x16 LP slots 
2 PCIe 5.0 x16 FHHL slots
M.22 M.2 PCIe 3.0 x4 NVMe slots (M-key 22110(default))
Drive Bays / Storage
Drive Bays ConfigurationDefault: Total 10 bays
2 front hot-swap 2.5" SATA drive bays 
8 front hot-swap 2.5" NVMe drive bays 
Option A: Total 8 bays
8 front hot-swap E1.S NVMe drive bays
M.22 M.2 NVMe slots (M-key)
System Cooling
FansN/A
Power Supply
6x 5250W6x 5250W Redundant Titanium (certification pending) Level (96%) power supplies
Operating Environment
Environmental Spec.Operating Temperature: 10°C ~ 35°C (50°F ~ 95°F)
Non-operating Temperature: -40°C to 60°C (-40°F to 140°F)
Operating Relative Humidity: 8% to 90% (non-condensing)
Non-operating Relative Humidity: 5% to 95% (non-condensing)

Streamline deployment at scale for AI & LLM

Built on Supermicro's proven AI building-block system architecture, the new 8-GPU system with the latest AMD Instinct™ and NVIDIA HGX™ GPUs streamline deployment at scale for the largest AI models and reduce lead time.

The 8-GPU air-cooled solution is feature maximized and power optimized supporting dedicated I/O and dedicated storage per GPU, full performance GPUs, CPUs, memory, and high-speed networking for large scale cluster deployments. These powerful GPUs enhance operations-per-second and performance-per watt at rack scale.

H14 8-GPU System

Next-Gen Large Scale AI Training Platform

  • Industry standard OCP Accelerator Module (OAM) with eight accelerators interconnected on an AMD Instinct™ and NVIDIA HGX™
  • Industry-leading up to 2TB HBM3e GPU memory in a single server node
  • 1:1 400G networking dedicated for each GPU designed for large scale AI and supercomputing clusters
  • Dual Socket AMD EPYC™ 9005/9004 Series Processors
  • Up to 24 DIMMs for up to 9 TB of DDR5 6000 memory
Anewtech-Systems-Supermicro-GPU-Server-PIe5-GPU-AI-Servers-AS-8126GS-TNMR

AS-8126GS-TNMR 
8U dual processor
with AMD Instinct™ MI325X GPUs

Anewtech-Systems-Supermicro-GPU-Server-PIe5-GPU-AI-Servers-AS-A126GS-TNBR

AS-A126GS-TNBR 
10U dual processor Server
with NVIDIA HGX™ B200 GPUs

 
Anewtech-Systems-Supermicro-AMD-9005-Servers_A-plus-server-brochure

Supermicro H14 Server Solutions

Accelerate Innovation: Up to 192 cores/384 threads, max 500W TDP per socket with AMD EPYC™ 9005 series processors

Download Brochure

Anewtech-Systems-Supermicro-AMD-9005-Servers_A-plus-server-whitepaper.

H14 White Paper

Leading Performance and Power Efficiency with Supermicro Solutions Featuring AMD AMD EPYC™ 9005 series processors

Download White Paper