From single GPUs to full racks. Sourced, delivered, commissioned.

We source and trade NVIDIA data-centre GPUs for our customers — H100, H200, B200, GB200 and their successors — together with the networking, storage and power equipment a cluster needs. Sourced through the Bitkern Group's supplier network, benchmarked on price, and delivered to your site or into a Castellan data centre, tested and ready for power-on. You own and operate the hardware; we handle everything up to that point.

The full bill of materials for an AI deployment.

AI projects lose months and budget in procurement: allocation queues, opaque pricing, freight and customs delays, and hardware that arrives before the site is ready — or long after. We run this layer as a professional supply-chain operation, from specification to installed, tested racks.

GPU & accelerator systems

NVIDIA HGX/DGX-class platforms — Blackwell and Hopper generations — specified, quoted and sourced through our supplier network.

Networking fabric

InfiniBand and RoCE-class Ethernet fabrics, optics, and cabling — sized for the cluster topology, not bought piecemeal.

Storage & data infrastructure

High-throughput parallel storage and NVMe tiers matched to training and inference I/O profiles.

Power & cooling equipment

PDUs, busway, CDUs, and direct-liquid-cooling components — the long-lead items that gate every deployment schedule.

H100 to GB300: the platforms we source and trade.

Castellan trades GPUs outright — single cards and servers, volume lots, and vetted secondary-market units — and delivers complete, integrated racks: HGX baseboards, NVL72 systems, networking and storage, cabled and burned in. Every current NVIDIA data-centre generation, specified to your workload:

Hopper

NVIDIA H100

80 GB HBM3, 3.35 TB/s memory bandwidth, 900 GB/s NVLink. The deployed workhorse of the AI build-out — deep trading liquidity and strong price-performance for training and inference.

Hopper

NVIDIA H200

141 GB HBM3e, 4.8 TB/s memory bandwidth. Drop-in HGX upgrade on the Hopper platform — the choice for long-context and memory-bound inference.

Blackwell

NVIDIA B200

180 GB HBM3e and 8 TB/s memory bandwidth per GPU in HGX B200 systems (1.44 TB per 8-GPU system), fifth-generation NVLink at 1.8 TB/s — for large-scale training.

Blackwell

NVIDIA GB200 NVL72

72 Blackwell GPUs and 36 Grace CPUs in one liquid-cooled, rack-scale system with a unified NVLink domain — delivered as complete racks, ready for power-on.

Blackwell Ultra

NVIDIA GB300 NVL72

72 Blackwell Ultra GPUs and 36 Grace CPUs, 20 TB of HBM3e per rack, fully liquid-cooled — built for reasoning inference at high throughput per rack.

Trading

GPU trading desk

Buy- and sell-side: we place surplus units for owners and source allocation for buyers — inspected, warranted where available, with clean documentation and logistics.

Why buyers procure through Castellan.

Allocation access

We draw on the Bitkern Group's supplier network, built over a decade of operations, to source allocation for our customers.

Price discipline

Multi-vendor benchmarking on every bill of materials. You see the comparison, not just the quote.

Vendor-neutral specification

Systems specified from your workload backwards — training, fine-tuning, or inference — not from a vendor's roadmap forwards.

Logistics & customs

EXW to DDP: freight, insurance, customs and staging across Swiss, EU and North American jurisdictions — handled as one accountable scope.

Integration & commissioning

Rack integration, burn-in and acceptance testing — in your own facility or in a Castellan Powered Shell or Turnkey data centre.

Lifecycle & warranty

Warranty management, spares strategy and refresh planning, so your systems stay productive over their full service life.

One accountable counterparty, from PO to power-on.

We work for enterprises building their first cluster, AI companies scaling an existing fleet, and institutions that need auditable, compliant procurement under Swiss or European contract law. Engagements run standalone or together with a data-centre lease from Castellan — Powered Shell & Turnkey — so hardware and facility arrive as one programme.

Scope

Specification · sourcing · logistics · commissioning · lifecycle

Hardware

GPU systems · networking · storage · power & cooling equipment

Commercial models

Agency (fee-based) or principal (purchase & resale) structures

Jurisdictions

Switzerland · Europe · North America

Contract law

Swiss or EU governing law · full contract documentation

Delivery

To your site or into a Castellan data centre

Need GPUs on a real timeline?

Tell us the workload, scale, and target date. We'll come back with a specified bill of materials, benchmarked pricing, and a delivery schedule you can plan against.