Skip to content

Home/GPU SERVER CATALOGUE

GPU SERVER CATALOGUE

The right GPU. The complete system.

Explore NVIDIA GPU families for custom servers, enterprise platforms and integrated HGX systems.

Request a quote Call +1 469 278 1240 WhatsApp +1 469 278 1240 (opens in a new tab)

Browse desktop RTX, professional RTX, data centre and previous-generation GPUs. Every enquiry starts with your workload; the quotation confirms the exact components, condition, availability and commercial terms.

How we configure your server ↗

NVIDIA Hopper

H100 & H200 GPU Servers

Purpose-built configurations for AI training, LLM inference, fine-tuning and high-performance computing.

NVIDIA manufacturer reference (opens in a new tab)

Quote this configuration ↗

NVIDIA H100 PCIe

PCIe server configurations, selected around your workload and platform requirements.

NVIDIA H100 NVL

Enterprise PCIe configurations with supported NVLink connectivity.

NVIDIA H100 SXM

Integrated HGX platforms for demanding multi-GPU workloads.

NVIDIA H200 NVL

PCIe configurations for memory-intensive AI and HPC applications.

NVIDIA H200 SXM

HGX platforms for large-model training, inference and scientific computing.

NVIDIA H20

A distinct Hopper server GPU enquiry; confirm the exact supported platform, software and supplied specification.

H100, H200 and H20 are distinct products. PCIe/NVL and SXM/HGX configurations need different server designs; the quotation identifies the actual GPU, interconnect and host.

NVIDIA Blackwell

B200 & B300 AI Platforms

Complete GPU server platforms for advanced AI training, reasoning, large-model inference and growing compute infrastructure.

NVIDIA manufacturer reference (opens in a new tab)

Quote this configuration ↗

NVIDIA HGX B200

Blackwell multi-GPU platforms with integrated high-bandwidth GPU interconnects.

NVIDIA HGX B300

Blackwell Ultra platforms for demanding AI training and inference infrastructure.

B200 and B300 are quoted as complete supported platforms, with power, cooling, networking and deployment requirements reviewed together.

Inference · Rendering · Virtualization

Enterprise AI & Graphics Servers

Enterprise GPU configurations for AI inference, visualization, rendering, video processing and supported virtual desktop deployments.

NVIDIA manufacturer reference (opens in a new tab)

Quote this configuration ↗

RTX PRO 6000 Blackwell Server Edition

A server-focused professional GPU for AI and visual computing workloads.

RTX PRO 4500 Blackwell Server Edition

A server variant for compatible enterprise and virtualized workloads; separate from RTX PRO 4500 Blackwell Workstation Edition.

NVIDIA L40S & L40

Enterprise options for AI, rendering and visualization.

NVIDIA L20

An Ada-generation server GPU option; confirm the exact host, application, driver and licensing requirements.

NVIDIA L4

A compact enterprise option for inference, video and visual computing.

NVIDIA A40 & A10

Previous-generation options for supported graphics, inference and virtualization workloads.

NVIDIA A16 & A2

Selected configurations for virtual desktop or inference requirements.

Virtualization features and software licenses depend on the selected GPU and deployment. We match the configuration to your application.

Blackwell RTX

GeForce RTX 50 Series

Custom RTX systems for game development, creative production and compatible local AI workloads.

NVIDIA manufacturer reference (opens in a new tab)

Quote this configuration ↗

GeForce RTX 5090

Custom configurations available to quote.

GeForce RTX 5080

Custom configurations available to quote.

GeForce RTX 5070 Ti

Custom configurations available to quote.

GeForce RTX 5070

Custom configurations available to quote.

GeForce RTX 5060 Ti

Specify your preferred memory variant when requesting a quote.

GeForce RTX 5060

Custom configurations available to quote.

GeForce RTX 5050

Custom configurations available to quote.

Chassis layout, card dimensions, power, cooling and software suitability are checked for the selected build.

Ada Lovelace RTX

GeForce RTX 40 Series

Explore custom systems for graphics production, rendering, development and compatible AI applications.

NVIDIA manufacturer reference (opens in a new tab)

Quote this configuration ↗

GeForce RTX 4090

Custom configurations available to quote.

GeForce RTX 4080 SUPER & RTX 4080

Choose the exact model for your configuration.

GeForce RTX 4070 Ti SUPER & RTX 4070 Ti

Choose the exact model for your configuration.

GeForce RTX 4070 SUPER & RTX 4070

Choose the exact model for your configuration.

GeForce RTX 4060 Ti & RTX 4060

Specify your preferred model and memory variant.

Multi-GPU systems are designed for applications that support them. Exact card models and availability are confirmed in your quotation.

Previous-generation RTX

GeForce RTX 30 & 20 Series

Budget-conscious RTX configurations for compatible development, graphics and compute requirements.

NVIDIA manufacturer reference (opens in a new tab)

Quote this configuration ↗

RTX 30 Series · Ampere

RTX 3090 Ti, RTX 3090, RTX 3080 Ti, RTX 3080, RTX 3070 Ti, RTX 3070, RTX 3060 Ti, RTX 3060 and RTX 3050.

RTX 20 Series · Turing

RTX 2080 Ti, RTX 2080 SUPER, RTX 2080, RTX 2070 SUPER, RTX 2070, RTX 2060 SUPER and RTX 2060.

Share your application and budget. The quotation specifies the exact memory variant, product condition, availability and warranty terms.

RTX PRO · RTX Ada · RTX A · Quadro RTX

Professional RTX Systems

Professional GPU configurations for CAD, 3D production, visualization, simulation and compatible AI workflows.

NVIDIA manufacturer reference (opens in a new tab)

Quote this configuration ↗

RTX PRO Blackwell

RTX PRO 6000 Blackwell Workstation Edition and Max-Q Workstation Edition; RTX PRO 5000 Blackwell; RTX PRO 4500 Blackwell Workstation Edition; RTX PRO 4000 Blackwell and SFF Edition; RTX PRO 2000 Blackwell.

RTX Ada Generation

RTX 6000, RTX 5000, RTX 4500, RTX 4000, RTX 4000 SFF and RTX 2000 Ada Generation.

RTX A Series · Ampere

RTX A6000, RTX A5500, RTX A5000, RTX A4500, RTX A4000, RTX A2000, RTX A1000 and RTX A400.

Quadro RTX · Turing

Quadro RTX 8000, Quadro RTX 6000, Quadro RTX 5000 and Quadro RTX 4000.

Workstation, Max-Q Workstation, Server and Laptop GPUs have different deployment and cooling requirements. Select the exact edition and supported host.

Ampere · Turing · Volta · Pascal

Previous-generation GPU Servers

Explore earlier-generation GPU systems for existing applications, research projects and budget-sensitive infrastructure.

Quote this configuration ↗

NVIDIA A100

40 GB and 80 GB variants in supported PCIe or SXM/HGX configurations.

NVIDIA A40, A30, A10, A16 & A2

Ampere-generation configurations selected for your compute, graphics or virtualization requirements.

NVIDIA T4

Turing-generation configurations for compatible inference, video and virtualization workloads.

NVIDIA V100 & V100S

Volta-generation systems for compatible AI and scientific applications.

NVIDIA P100, P40 & P4

Pascal-generation options for compatible existing workloads.

Legacy systems are selected around software compatibility. Product condition, availability and warranty terms are specified in your quotation.

COMPLETE NVIDIA-BRANDED SYSTEMS

NVIDIA DGX Blackwell Systems

Request an exact complete-system quotation for NVIDIA DGX B200 or DGX B300.

NVIDIA manufacturer reference (opens in a new tab)

Quote this configuration ↗

NVIDIA DGX B200

A complete NVIDIA-branded B200 system; separate from an OEM HGX B200 server.

NVIDIA DGX B300

A complete NVIDIA-branded Blackwell Ultra system; confirm the actual unit, configuration and delivery scope.

Specify the exact DGX system, configuration, equipment condition and included software/support for your quote.

GRACE CPU + BLACKWELL GPU SYSTEMS

Grace Blackwell NVL Platforms

Distinct NVL4 and rack-scale NVL72 system enquiries, with facilities and software requirements reviewed together.

NVIDIA manufacturer reference (opens in a new tab)

Quote this configuration ↗

NVIDIA GB200 NVL72

A liquid-cooled rack-scale Grace Blackwell platform; not an HGX B200 server or an ordinary add-in card.

NVIDIA GB300 NVL72

A distinct liquid-cooled rack-scale Grace Blackwell Ultra platform.

NVIDIA GB200 NVL4

A separate platform combining four Blackwell GPUs and two Grace CPUs; not an NVL72 rack.

Specify the exact platform and complete system. Review Arm software compatibility, rack space, cooling, power and networking for the proposed deployment.

NVIDIA DGX H100 / H200

NVIDIA DGX Hopper Systems

NVIDIA-branded complete-system enquiries, distinct from OEM servers based on HGX.

NVIDIA manufacturer reference (opens in a new tab)

Quote this configuration ↗

NVIDIA DGX H100

Request the exact DGX H100 complete-system configuration and disclosed unit condition.

NVIDIA DGX H200

Request the exact DGX H200 complete-system configuration and disclosed unit condition.

Include the intended software stack, networking, rack power/cooling and support scope in your brief.

GRACE CPU + HOPPER GPU

GH200 Grace Hopper Systems

GH200 systems combine an Arm-based Grace CPU and Hopper GPU through NVLink-C2C.

NVIDIA manufacturer reference (opens in a new tab)

Quote this configuration ↗

NVIDIA GH200 Grace Hopper Superchip

An integrated CPU+GPU platform; separate from a standalone H200 GPU.

NVIDIA GH200 NVL2

A system connecting two GH200 superchips; confirm the exact memory/platform variant and supported software.

Specify the supported host, CPU/GPU memory variant, Arm software stack, interconnect and deployment requirements.

LET'S CONFIGURE YOUR NEXT SYSTEM

Start with your workload.
We'll talk hardware.

Tell us what you need to run, where you need it and your budget.

Get a configured quote Call +1 469 278 1240 WhatsApp +1 469 278 1240 (opens in a new tab)
CONFIGURATION & QUOTATIONSNeed help choosing your hardware?Share your model, part number or project requirements.Request a quote

Tell us what you need

Our team will confirm the exact configuration, condition, delivery and warranty terms in your quotation.

Call +1 469 278 1240WhatsApp requirements ↗
Add purchase, rental or project details optional

We use these details to respond to your enquiry. Privacy policy. Fields marked * are required.

Prefer the detailed enquiry form? ↗

Call GPU WORLD WhatsApp