# Line below added 29 Nov 2024
AHGX | ESC8000A-E13X

AHGX - AMD EPYC™ 9005 series Turin CPU - NVIDIA H200 / NVIDIA RTX PRO™ 6000 Blackwell Server Edition - 4U Form Factor Key Features NVIDIA RTX PRO™ Server: Powered by the gr

AHGX

- AMD EPYC™ 9005 series Turin CPU

- NVIDIA H200 / NVIDIA RTX PRO™ 6000 Blackwell Server Edition

- 4U Form Factor

Key Features

  • NVIDIA RTX PRO™ ServerPowered by the groundbreaking NVIDIA RTX PRO Blackwell GPUs and ConnectX®-8 SuperNIC Switch Board, ESC8000A-E13X delivers multifold performance boosts enterprise and industrial AI workloads with unmatched efficiency.
  • Extreme GPU Connectivity: Configured with ConnectX®-8 SuperNICs and built-in PCIe switch, provides eight QSFP ports with 400 Gb/s and PCIe Gen6 connectivity for GPU-to-GPU communication. 
  • Optimized Server Configuration: Fully compliant with NVIDIA MGXTM architecture with 2-8-5 topology (CPU-GPU-DPU/NIC), it can enable multiple configurations and rapidly deploy in large-scale enterprise or industrial AI infrastructures.
  • 5th Gen AMD EPYCTM Processors: Powered by AMD EPYC 9005 series processors with up to 192 Zen 5/5c cores and support for a maximum TDP of 500 watts per socket.
  •  Toolless DesignThe exclusive toolless design empowers easy service and saves maintenance time for maximum efficiency.

Target market

 • AI Factory
 • Enterprise Workloads
 • Agentic & Generative AI
 • LLM Inference
 • Industrial & Physical AI
 • Digital Twins

Supercharge your system with extreme GPU to GPU connectivity

AHGX features the NVIDIA ConnectX®-8 SuperNICs, the groundbreaking fusion of PCIe 6.0 switching speed and up to 800Gb/s GPU-to-GPU networking bandwidth by a single chip. This innovative switch eliminates the complexity of discrete PCIe components, slashing system design overhead while doubling GPU-to-GPU bandwidth for seamless, low-latency collective communications — delivering higher performance compared to legacy architectures.

System Layout


Panel Layout


AHG Block Diagram

Powered by AMD EPYC™ 9005 processors,AHGX delivers exceptional performance, featuring top-tier GPUs, faster GPU interconnects, and higher-bandwidth fabric. This powerhouse server supports up to eight dual-slot NVIDIA RTX PRO™ Blackwell GPUs, and offers peak GPU to GPU communication performance with ConnectX®-8 SuperNICs and built-in PCIe Gen 6 switches. This configuration allows seamless scaling and performance enhancement, making ESC8000A-E13X an ideal choice for tackling most Enterprise AI and HPC tasks.

Scale with ease and flexibility using MGX architecture

AHGX takes AI infrastructure to the next level by leveraging NVIDIA® MGX™, an open and flexible reference design that ensures future-proof compatibility. With its innovative modular architecture, clients can easily tailor their solutions to meet specific AI and high-performance computing needs. MGX sets a new industry benchmark for modular server design, enhancing ROI and slashing time to market - empowering businesses to stay ahead in the fast-evolving AI landscape.


Processor / System Bus

2 x Socket SP5 (LGA 6096)

AMD EPYC™ 9005 series processors*

* Up to 500W TDP, TDP support varies by configuration


Memory

Total Slots: 24 (12 channel per CPU, 12 DIMM per CPU)

Capacity: Maximum up to 3TB per CPU socket

Memory Type: DDR5 6400/5600 RDIMM

Memory Size: 128GB, 96GB, 64GB, 32GB, 16GB RDIMM


Expansion Slots

Up to 10 slots

Rear:

8 x PCIe x16 for dual-slot GPU cards (Gen6 x16 link, FH/FL)

1 x PCIe x16 for NIC/BlueField-3 cards (Gen5 x16 link, FH/HL)

Front:

1 x PCIe x16 (Gen5 x8 link, FH/HL)


Storage

8 x 2.5" Front Hot-swap Storage Bays

Default SKU*: Backplane supports up to 8 x NVMe

*MGX compliance

2 x M.2 Socket, supports up to 22110 type (PCIe Gen5 x4 link)

(M.2 board supports up to 2 x NVMe)


Networking

8 x 400Gbps ports (QSFP, ConnectX®-8)

2 x 10GbE LAN ports (RJ45, X710-AT2)

1 x Management Port

Multi-GPU Support

Up to 8 x NVIDIA RTX PRO™ 6000 Blackwell Server Edition GPU Cards*

*Support short GPU brackets only


Front I/O Ports

1 x Mini DisplayPort

2 x USB 5Gbps ports

1 x Debug port


Rear I/O Ports

8 x QSFP ports

1 x USB 5Gbps port

2 x RJ-45 LAN ports

1 x RJ-45 management LAN port


Switch/LED

Front:

1 x Power switch/LED

1 x Location switch/LED

1 x Message LED

1 x Clear CMOS switch

1 x Reset Switch

2 x M.2 LEDs

2 x LAN LEDs

1 x Q-code/Port 80 LED

Rear:

1 x Power switch/LED

1 x Location switch/LED

1 x Message LED

8 x QSFP LED

OS Support


Management Solution

Control Center Enterprise (in-band)

ASMB12-iKVM for (out-of-band/BMC AST2600)


Regulatory Compliance

BSMI, CB, CE, FCC(Class A), RCM


Dimensions

800mm x 439.5mm x 175mm

31.5” x 17.3” x 6.9”


Form Factor

4U


Weight

Net Weight: 42 Kg

Gross Weight: 45 Kg


Power Supply

3+1 redundant 3200W 80 PLUS Titanium power supply

220-240 Vac, 16A (x4) 50/60Hz


Environment

Operating temperature: 10°C ~ 35°C

Non-operating temperature: -40°C ~ 60°C

Non-operating humidity: 20% ~ 95% (Non-condensing)

*For operating temperatures above 30°C, please contact your local sales representative


Datasheet 1
Title Version Date Size
AHGX Brochure
CATALOGUE 1
Title Version Date Size
Product Catalog

AHGX | ESC8000A-E13X

  • AMD EPYC 9005 Series Processors
  • 4U NVIDIA RTX PRO Server with ConnectX®-8 SuperNICs 
  • supports eight dual-slot NVIDIA RTX PRO 6000 Blackwell Server Edition and H200 GPUs
  • eight 400Gb/s QSFP ports for GPU-to-GPU networking 
  • 24 DIMM slots 
  • eight PCIe 6.0 slots 
  • two PCIe 5.0 slots 
  • eight 2.5-in NVMe drives

  • $USD $31,600.00

    *RRP Pricing*

    To View Channel Discounts Please Login


System Configurator


Tags: AHGX, ESC8000A-E13X, AMD EPYC 9005 series CPU, PCIe 6.0, GPU, HPC Server, AI, H200, NVIDIA RTX PRO™ 6000 Blackwell Server Edition, GPU