Single-tenant physical servers (standard, compute and storage configurations, 64–512 GB RAM) with full root access, IPv4 and IPv6, remote power cycling, serial console and network recovery mode. Billed monthly, quarterly or yearly.
FluffyStack toolsJurisdictional exposure
Sub-services (4)
Standard Dedicated Server
8-core server with 64 GB RAM for general-purpose workloads
Compute Dedicated Server
24-core server with 128 to 512 GB RAM for CPU-heavy workloads
Storage Dedicated Server
16-core server with 256 GB RAM and up to 273.4 TB of disk
Remote Server Management
Instant power cycling, serial console and network recovery mode via the control panel
Compliance & Certifications
This service is attested for the following frameworks. Always verify with the provider before relying on a specific compliance posture.
Where this runs
Commercial regions (4)
Europe (3)
- Amsterdam
- Cambridge
- London
North America (1)
- Fremont
Tags
Equivalent services on other platforms
Single-tenant dedicated servers (Advanced, Storage, Professional, GPU and Ready families) with root access and 1–10 Gb/s connectivity, billed monthly and hosted in Aruba's owned data centres in Arezzo and Bergamo, Italy.
Single-tenant dedicated physical servers for workloads that require hardware-level isolation, licence-bound software, or specialised architectures; SecNumCloud-qualified across the standard configurations
Dedicated single-tenant 8-GPU servers for large-scale AI training and inference, provisioned on contract
Single-tenant dedicated physical servers provisioned via API, with predictable performance and no hypervisor overhead — supports custom hardware configurations on request
Dedicated bare-metal hardware connected to Google Cloud via low-latency links, engineered for running Oracle Database, SAP HANA, or other legacy enterprise workloads that cannot run in standard virtualised environments, with Google Cloud-managed operations
Dedicated root servers (AX, EX, SX, GPU and other lines) managed via Hetzner Robot, with full hardware control, RAID and OS installation options, and optional vSwitch coupling to Cloud Networks
Sales-led, reserved bare-metal NVIDIA GPU capacity (e.g. GB300 NVL72 racks and B200 hosts) ring-fenced per project and region on InfiniBand/NVLink fabrics, delivered via Nscale Kubernetes Service, Managed Slurm or bare metal for large-scale training and inference.
Bare-metal provisioning service that manages physical servers through the same API surface as Nova VMs, with PXE/virtual-media boot, IPMI/Redfish power management and image deployment via the direct (HTTP) agent, ramdisk or Anaconda deploy interfaces
Bare-metal and virtual machine compute instances on Oracle Cloud Infrastructure — Intel/AMD x86 plus Ampere A1 ARM shapes, GPU instances (NVIDIA A10/A100/H100/RTX PRO), per-second billing, and an always-free tier covering 4 OCPU ARM allocation
Dedicated physical servers with full hardware control, custom RAID and partitioning, IPMI/KVM access, free anti-DDoS protection, and server ranges from entry-level to NVMe
Dedicated bare-metal servers delivered via the Scaleway console / API within minutes, with hourly or monthly billing, native VPC attachment, and full hardware control for workloads needing strict tenancy isolation
Scaleway's long-standing range of monthly-billed dedicated servers (Start, Pro, Core, Store and GPU ranges) with optional commitment discounts, plus Dedibox VPS
Dedicated Apple Mac mini servers (M1, M2, M2 Pro, M4, M4 Pro) as a service in Paris, without hypervisor, billed hourly with a 24-hour minimum allocation required by Apple's macOS licence
Single-tenant physical servers with hourly billing, BMC / IPMI access, and free DDoS protection deployed within minutes via the same dashboard as Cloud Compute