Core 48
Core 48 is the package most teams start with: a single AMD EPYC 9454P with 48 cores and 96 threads, 256 GB of ECC memory and two 3.84 TB datacentre NVMe drives in a mirror. It runs a busy SaaS backend, a primary Postgres with headroom, or a cluster of containers that used to be twenty cloud instances.
No setup fee. Monthly billing, three-month minimum, then cancel with 30 days notice. Delivery within 48 hours.
- Processor
- AMD EPYC 9454P
- Cores
- 48 cores / 96 threads
- Memory
- 256 GB DDR5 ECC
- Storage
- 2 × 3.84 TB NVMe (mirrored)
- Network
- 10 Gbit, 20 TB included
- Response
- Engineer within 30 min
Datasheet
Exact configuration as delivered. Variants within a series are quoted individually.
- Processor
- AMD EPYC 9454P, 48 cores / 96 threads, Zen 4, 2.75 GHz base, up to 3.8 GHz boost
- Memory
- 256 GB DDR5 ECC registered
- Storage
- 2 × 3.84 TB NVMe SSD, datacentre edition, software mirror (RAID 1)
- Usable capacity
- about 3.5 TB after mirroring and filesystem overhead
- Network
- 10 Gbit uplink, 20 TB outbound per month included, then €1 per TB
- Addresses
- 1 IPv4 and a /64 IPv6 block; private VLAN to other Infraexa servers
- Location
- Germany (Falkenstein or Nuremberg) or Finland (Helsinki)
- Operating system
- Ubuntu LTS, Debian or Rocky Linux, hardened to the Infraexa baseline
- Backups
- Nightly encrypted snapshots to a second site, 30-day retention
- Incident response
- Critical issues answered by an engineer within 30 minutes, around the clock
What Core 48 is for.
Workloads this configuration has been sized for, and what it adds beyond the standard layer.
Best for
- SaaS backends consolidating cloud instances
- Primary Postgres or MySQL with replicas on a second Core
- Container platforms with 50 to 150 services
- CI fleets that outgrew hosted runners
Included beyond the standard layer
The standard layer is the whole offer here: hardening, patching, observability, backups, security, engineers and Exa. Add managed Postgres, object storage or longer retention from the add-ons list on the pricing page.
Included with every package.
Nothing on this list is an upsell.
Solutions built on this package.
AI inference and fine-tuning
A dedicated 96 GB GPU with the inference stack installed, monitored by people who have run it before.
SaaS backends
Consolidate compute, database and cache on dedicated hardware, keep your deploy workflow, cut the bill in half or better.
Databases and analytics
Large databases are the first thing that gets expensive in the cloud and the first thing that gets fast on dedicated NVMe.
Agencies and development shops
One Cluster 3 or a set of Core servers with namespaces per client, and an operations team your clients never need to meet.
Guides for this kind of server.
Managed vs unmanaged dedicated servers: the true monthly cost
A line-by-line comparison of what a bare dedicated server costs once monitoring, backups, security tooling and engineer time are added.
Read the guideDedicated servers vs cloud for a SaaS with a €20,000 monthly bill
A worked migration of a typical SaaS from hyperscaler instances, managed database and egress to a few dedicated servers, with the before-and-after numbers.
Read the guideWhat it takes to run a wholesale dedicated server in production
The checklist a competent operations engineer works through between receiving a root password and trusting a dedicated server with production traffic.
Read the guideOther packages.
- Store 300Store
308 TB of raw disk behind 15 TB of NVMe cache, run as object or block storage.
- CPU
- 32 cores / 64 threads
- Memory
- 256 GB DDR4 ECC
- Storage
- 14 × 22 TB HDD + 2 × 7.68 TB NVMe
€3,290per month - Enterprise 48Enterprise
Core 48 compute in an enterprise chassis with redundant power and four hot-swap NVMe bays.
- CPU
- 48 cores / 96 threads
- Memory
- 256 GB DDR5 ECC
- Storage
- 4 × 3.84 TB NVMe (hot-swap)
€3,860per month - Core 48 MaxCore
512 GB of memory and 30 TB of NVMe for in-memory data and large databases.
- CPU
- 48 cores / 96 threads
- Memory
- 512 GB DDR5 ECC
- Storage
- 2 × 15.36 TB NVMe (mirrored)
€4,120per month - Accel 96Accel
A 96 GB Blackwell GPU with 512 GB of system memory, ready for inference day one.
- CPU
- 24 cores / 48 threads
- Memory
- 512 GB DDR5 ECC
- GPU
- NVIDIA RTX PRO 6000 Blackwell, 96 GB
€6,780per month - Cluster 3Cluster
Three 48-core nodes on a private network with highly available Kubernetes and Postgres.
- CPU
- 144 cores / 288 threads total
- Memory
- 384 GB DDR5 ECC total
- Storage
- 6 × 1.92 TB NVMe total
€9,850per month
Ready to run Core 48? Tell us about the workload.
A quote within one business day. €2,540 per month with everything included, no setup fee.