Uvation MarketplaceMarketplace

Supermicro AS-4126GS-NB3RT-LCC GPU Server

Liquid-cooled 4U server combining eight NVIDIA Blackwell Ultra GPUs with dual AMD EPYC 9005/9004 processors for AI training, inference and HPC.

GPUs
8x
GPUs
HBM3e
2.3 TB
HBM3e
DDR5 memory
6 TB
DDR5 memory

AMD EPYC Meets Liquid-Cooled HGX B300

Supermicro’s AS-4126GS-NB3RT-LCC brings eight Blackwell Ultra GPUs and dual AMD EPYC processors together in a direct-to-chip liquid-cooled 4U chassis.

192 Cores per Processor, Liquid-Cooled

AMD EPYC 9005 processors deliver up to 192 cores and 384 threads each, with liquid-cooled CPUs up to 500 W TDP.

6 TB of DDR5 Close to the GPUs

24 DDR5 ECC RDIMM slots reach 6 TB at 6400 MT/s with EPYC 9005, beside 8 E1.S NVMe bays.

Cold Plates Where the Heat Lives

Direct-to-chip cold plates cool the CPUs and HGX B300 GPUs, backed by up to four hot-swappable rear fans.

Eight Blackwell Ultra GPUs,
Fully Meshed

Fifth-generation NVLink with NVSwitch links all eight GPUs at up to 1.8 TB/s GPU-to-GPU bandwidth.

Rear view of the liquid-cooled AS-4126GS-NB3RT-LCC with coolant hoses
8×
Blackwell Ultra SXM GPUs
288 GB
HBM3e per GPU
1.8 TB/s
GPU-to-GPU NVLink
4U / D2C
Cold-plate liquid cooled

Workloads

Built for the workloads that matter, from deep learning to climate modeling and healthcare research.

Deep Learning Training and Inference

Eight HGX B300 GPUs with 2.3 TB of HBM3e handle large-model training and high-throughput inference in one 4U system.

Climate Modeling and Scientific Research

Dual AMD EPYC processors with up to 192 cores each and 6 TB of DDR5 power simulation-heavy HPC research.

Healthcare and Industrial Automation AI

PCIe 5.0 CPU-to-GPU links and 800 Gb/s SuperNICs move data quickly for healthcare analytics and industrial automation models.

Engineered to dominate

Dense Compute,
Liquid-Cooled by Design

Blackwell Ultra GPUs, AMD EPYC compute and eight 800 Gb/s SuperNICs run sustained workloads inside a compact, cold-plate-cooled 4U footprint.

Cutaway view of the liquid-cooled AS-4126GS-NB3RT-LCC chassis
384 MB
Cache per CPU
6400 MT/s
DDR5 memory speed
96%
Titanium PSU efficiency
800 Gb/s
8× ConnectX-8 SuperNICs
Cutaway view of the liquid-cooled AS-4126GS-NB3RT-LCC chassis
384 MB
Cache per CPU
6400 MT/s
DDR5 memory speed
96%
Titanium PSU efficiency
800 Gb/s
8× ConnectX-8 SuperNICs

The rack, itemized.

SUBSYSTEM

SPECIFICATION / CONFIGURATION DETAILS

Processor

2× AMD EPYC 9005 or 9004 processors

Operating System

ESXi 8.0U3, ESXi 9.0, RHEL 10.0

Chipset

System on Chip (SoC)

Accelerators / GPU

NVIDIA SXM: HGX B300 8-GPU (288GB)

Memory

24 DIMMs; up to 6 TB

Primary Storage

8 front hot-swap E1.S PCIe 5.0 x4 NVMe drive bays

Secondary Storage

2 M.2 NVMe slots

Security

Trusted Platform Module (TPM) 2.0; Silicon Root of Trust (RoT) – NIST 800-193 Compliant

Chassis

CSE-GP405LTS-R000NP

Power Supply

4× 6600W Redundant (2 + 2) Titanium Level (96%) power supplies

Ports

8× OSFP; 2× 10GbE; USB; VGA; Mini DisplayPort, TPM Header

Slots / PCIe Architecture

2 PCIe 5.0 x16 FHHL slots

Bezel

Not specified (a separate front security bezel is not specified by Supermicro)

Form Factor

4U Rackmount

Network Card

8x NVIDIA ConnectX®-8 SuperNICs (up to 800Gb/s)

Warranty

3-Year Labor, 1-Year Parts & 1-Year Advance Cross-Shipment Limited Manufacturer Warranty

Nuclear-Ready, Plug and Play AI Factories

Bypass grid constraints with self-contained, high-density inference ready infrastructure directly adjacent to clean, base load nuclear power.

Global Deployment Engine

Any Infra, Anywhere in the world.

Global Shipping and Deployment Capability treats advanced infrastructure as mobile, modular freight.

Packaged complex computing nodes, cooling manifolds, and power distribution units into certified, standard form factors.

360° Service Ecosystem

Unifying Legacy with Next-Gen Compute.

Vertically integrated service ecosystem that serves as an operational bridge between legacy environments and next-generation, AI-native infrastructure.

Finance and Leasing

Capital-as-a-Service for High-Density Compute

Convert upfront capital expenditures (CapEx) into predictable operating expenses (OpEx).

Uvation allows enterprises and sovereign entities to deploy multi-megawatt AI factories and advanced GPU clusters without liquidity constraint.