Skip to content
HomeSolutionsAI WorkstationsNexus Dual RTX 5090 Threadripper PRO Liquid-Cooled AI Workstation
Nexus Compute

Nexus Dual RTX 5090 Threadripper PRO Liquid-Cooled AI Workstation

Twin liquid-cooled 5090s for teams running training and serving at once.

Full manufacturer warrantyAuthorized channel48-hour quote

We help you choose, configure, and deliver the right system — no obligation.

Nexus Dual RTX 5090 Threadripper PRO Liquid-Cooled AI Workstation — Nexus Compute enterprise hardware
Nexus Dual RTX 5090 Threadripper PRO Liquid-Cooled AI Workstation hardware detail 1
Nexus Dual RTX 5090 Threadripper PRO Liquid-Cooled AI Workstation hardware detail 2
Nexus Dual RTX 5090 Threadripper PRO Liquid-Cooled AI Workstation hardware detail 3

Configuration at a Glance

GPU2× NVIDIA RTX 5090 — 64GB combined GDDR7
GPU InterconnectDual PCIe Gen5 x16 (full-bandwidth slots)
CPUAMD Threadripper PRO 7965WX (24-core)
Memory256GB DDR5 ECC

Tailored per engagement. Full technical overview below.

Configuration Options

Core specifications for this system. Every component is configurable to your workload — request a quote for a tailored build.

GPU / Accelerator

2× NVIDIA RTX 5090 — 64GB combined GDDR7

Processor

AMD Threadripper PRO 7965WX (24-core)

Memory

256GB DDR5 ECC

Storage

8TB PCIe Gen5 NVMe SSD

Overview

This workstation pairs two NVIDIA RTX 5090 GPUs with an AMD Threadripper PRO processor under a closed-loop liquid-cooling design built for sustained dual-GPU thermals. Nexus Compute sources every component through authorized channels and validates the full configuration end to end so it arrives as a stable, production-ready system.

Who This Solution Is For

AI teams scaling past a single GPU
Studios running high-throughput generative pipelines
Startups fine-tuning mid-to-large models in-house
Agencies serving multiple client workloads in parallel

Business Benefits

Two workloads in parallel

Serve a model on one GPU while training or experimenting on the other, eliminating queues between team members.

Sustained clocks under load

Liquid cooling holds both GPUs near boost clocks during long training runs that would throttle an air-cooled build.

Validated, not improvised

We test the dual-GPU thermal and driver stack before delivery so day-one stability is assured.

Typical Business Use Cases

1

Parallel fine-tuning across two GPUs

2

Full-precision inference on larger LLMs

3

High-throughput batch image and video generation

4

Serving production while developing a second model

Industry Applications

AI & Machine LearningMedia & EntertainmentSaaS & Software

Technical Overview

Two NVIDIA RTX 5090 GPUs (64GB combined GDDR7) ride an AMD Threadripper PRO 7000WX platform with 128 PCIe Gen5 lanes feeding both cards at full x16. A closed-loop liquid-cooling loop and 256GB of DDR5 ECC support sustained dual-GPU training and inference.

GPU2× NVIDIA RTX 5090 — 64GB combined GDDR7
GPU InterconnectDual PCIe Gen5 x16 (full-bandwidth slots)
CPUAMD Threadripper PRO 7965WX (24-core)
Memory256GB DDR5 ECC
Storage8TB PCIe Gen5 NVMe SSD
CoolingClosed-loop liquid cooling (CPU + GPUs)
Form FactorFull-tower workstation
Power2000W 80+ Titanium
Warranty3-year on-site, next-business-day

Specifications are indicative and configured to each engagement. Request a quote for a configuration tailored to your requirements.

Warranty, Support & Fulfillment

Every system ships from an authorized channel, configured and tested, with the documentation enterprise buyers need — backed by warranty and a dedicated account team.

Enterprise Warranty

Full manufacturer warranty with optional on-site, next-business-day support and extended coverage.

Authorized Channel

Sourced through Tier-1 distribution and OEM partners — never grey market. Asset & warranty records included.

Lead Time & Deployment

48-hour quotes, then configured, burn-in tested, and delivered on a committed schedule.

Nationwide Fulfillment

Coordinated logistics, rack-and-stack, and delivery wherever your infrastructure lives.

Frequently Asked Questions

Why liquid cooling for two 5090s?

Each RTX 5090 draws 575W, so two cards under sustained load generate heat that liquid cooling dissipates far more effectively than air, keeping clocks high and acoustics lower during long runs.

Do the RTX 5090s use NVLink?

No. The RTX 5090 has no NVLink; the cards communicate over PCIe Gen5, and the Threadripper PRO platform supplies the lanes to run both at full x16 simultaneously.

When should I choose this over a single-GPU workstation?

Choose dual GPUs when you need to run more than one workload at a time, fine-tune larger models, or sustain higher throughput than a single card delivers.

Hardware Assistance

Configure the Nexus Dual RTX 5090 Threadripper PRO Liquid-Cooled AI Workstation with Nexus Compute

Tell us your requirements and a hardware specialist will help you specify, configure, and quote the right system — typically within two business days. No obligation.