NVIDIA · CUDA · Bare-metal

GPU Dedicated Servers

Bare-metal servers with NVIDIA GPUs for LLM inference, model training, Stable Diffusion, 3D rendering and video transcoding. Full hardware access, no virtualization layer, no vGPU sharing. Deployment in 1–4 hours.

from $340.00 /mo

Need a different configuration — more VRAM, several cards, a specific CPU or more storage? Contact support and we will assemble it for your workload.

🎯
Dedicated GPU
The card is yours alone. No vGPU slicing, no MIG partitions, no noisy neighbours competing for VRAM.
🔓
Root + IPMI
Install any CUDA version, driver branch or container runtime. Custom ISO via IPMI if you need it.
♾️
Unmetered traffic
Pull datasets and push checkpoints without watching a bandwidth counter.
💳
Crypto payment
BTC, ETH, USDT and cards. Registration takes an email address.

GPU server plans

Prices shown with the annual payment discount. All configurations include NVMe storage, DDoS protection and unmetered traffic.

MEMORY
GPU
CPU
STORAGE
PRICE
🇳🇱 WG-1 - RTX 2080 TI
GPU for rendering & streaming
🧠64 GB RAM
GPU
Gigabyte RTX 2080 Ti
11 GB VRAM
CPU
12 vCore · AMD Ryzen 9 3900X · 3.8 GHz
24 threads
STORAGE
💾2 × 500 GB NVMe
PRICE
$340.00 /mo
$400.00 %
🇩🇪 GEX44-1 - NVIDIA RTX 4000
GPU for rendering & inference
🧠64 GB RAM
GPU
NVIDIA RTX 4000 SFF Ada
20 GB VRAM
CPU
14 vCore · Intel Core i5-13500 · 4.8 GHz
20 threads
STORAGE
💾2 × 1.92 TB NVMe
PRICE
$637.50 /mo
$750.00 %
🇳🇱 WG-2 - RTX 5070 TI
GPU for AI & Stable Diffusion
🧠64 GB RAM
GPU
NVIDIA RTX 5070 Ti
16 GB VRAM
CPU
12 vCore · AMD Ryzen 9 9900X · 4.4 GHz
24 threads
STORAGE
💾2 × 960 GB NVMe
PRICE
$680.00 /mo
$800.00 %
🇫🇮 GEX131-1 - NVIDIA RTX PRO 6000
GPU for LLM & model training
🧠256 GB RAM
GPU
NVIDIA RTX PRO 6000 Blackwell
96 GB VRAM
CPU
24 vCore · Intel Xeon Gold 5412U · 4.8 GHz
48 threads
STORAGE
💾2 × 960 GB NVMe
PRICE
$3,230.00 /mo
$3,800.00 %
🇩🇪 GEX131-1 - NVIDIA RTX PRO 6000
GPU for LLM & model training
🧠256 GB RAM
GPU
NVIDIA RTX PRO 6000 Blackwell
96 GB VRAM
CPU
24 vCore · Intel Xeon Gold 5412U · 4.8 GHz
48 threads
STORAGE
💾2 × 960 GB NVMe
PRICE
$3,230.00 /mo
$3,800.00 %

Which GPU fits your workload

The deciding factor is almost always VRAM, not raw compute — a model that does not fit in memory will not run at any speed.

GPUVRAMBest forRough guidance
NVIDIA RTX 2080 Ti 11 GB Video transcoding, 3D rendering, computer vision, small quantised models The cheapest way to get a real GPU. Fine for inference of 7B-class models in 4-bit quantisation.
NVIDIA RTX 5070 Ti 16 GB Stable Diffusion / SDXL, video generation, mid-size LLM inference Current Blackwell generation. Comfortable for image and video pipelines.
NVIDIA RTX 4000 SFF Ada 20 GB Continuous inference workloads, SDXL, professional rendering Low power draw, built for 24/7 duty rather than burst loads.
NVIDIA RTX PRO 6000 Blackwell 96 GB Training, fine-tuning, large LLMs without quantisation The only configuration here that handles 70B-class models in reduced precision and real fine-tuning runs.

What people run on these servers

🤖

LLM inference

Self-hosted Llama, Qwen, Mistral or DeepSeek behind vLLM, Ollama or TGI. Your prompts and your data never leave your machine — the usual reason teams move off hosted APIs.

🎨

Image and video generation

Stable Diffusion, SDXL, ComfyUI, Flux. A dedicated card means no queue and no per-image billing.

🎬

Rendering and transcoding

Blender Cycles, NVENC pipelines, batch video processing. NVENC offloads encoding from the CPU entirely.

📊

Training and fine-tuning

LoRA and QLoRA runs, computer vision models, custom architectures. 96 GB of VRAM removes most memory-related constraints.

🔬

Scientific computing

CUDA workloads, molecular dynamics, simulation, numerical modelling.

🕹️

Remote workstation

GPU-accelerated CAD, 3D and video editing over a remote desktop protocol.

Why bare metal instead of a GPU cloud

Predictable cost

A fixed monthly price instead of per-second billing. A long training run does not turn into a surprise invoice.

Full VRAM available

Cloud providers slice cards with vGPU or MIG. Here the entire card and all of its memory belong to one tenant.

No spot interruptions

Nobody reclaims your instance mid-run because a higher bidder appeared.

Your data stays put

No shared storage layer, no cross-tenant snapshots. Relevant for anything under NDA or GDPR.

Available locations

GPU configurations are available in the following data centres. Choose the one closest to your users or your data.

How to get started

1

Pick a configuration

Choose by VRAM first — it decides what actually fits. CPU and storage matter less for most GPU workloads.

2

Pay

Crypto, SBP or card. Payment is confirmed automatically.

3

Get access

Root credentials and IPMI details arrive by email within 1–4 hours. Ask support and we will pre-install the CUDA stack.

Frequently asked questions

Is the GPU dedicated or shared?
Dedicated. The physical card is passed through to your server — no vGPU slicing, no MIG partitioning, no time-sharing with other tenants. All VRAM and all compute belong to you.
Are CUDA and the drivers pre-installed?
On request. Tell support which CUDA version and driver branch you need and we will prepare the server before handover. Otherwise you get a clean OS and install the stack yourself — you have root.
Which model sizes fit in memory?
As a rough guide: 11–16 GB handles 7B-class models in 4-bit quantisation, 20 GB is comfortable for 13B-class, and 96 GB runs 70B-class models in reduced precision and supports real fine-tuning. Actual limits depend on context length, batch size and the inference engine.
Can I run several GPU cards in one server?
Multi-GPU configurations are available on request. Contact support with your requirements — lead time is typically 3–14 days depending on parts availability.
Can I use it for mining?
No. Cryptocurrency mining is prohibited by our Terms of Service on all plans, including GPU configurations.
How long does deployment take?
One to four hours after payment, depending on the configuration and hardware availability. GPU servers are provisioned manually, unlike VPS.
Can I upgrade to a bigger GPU later?
You can move to a higher plan — this means migrating to a different physical machine, so plan for downtime and data transfer. Support will help schedule it.

Not sure which card you need?

Describe your workload to support — model, framework, expected load — and we will tell you which configuration fits and whether a cheaper one would do the job.

Renting a GPU server: what to know before you order

How a GPU server differs from a regular dedicated server

A conventional dedicated server relies on the CPU, which executes a small number of complex operations at a time. A graphics card works the opposite way: thousands of simpler cores run in parallel. That architecture is what makes GPU hosting the default choice for neural networks, since training and inference come down to matrix multiplication — a task that parallelises almost perfectly.

This does not mean a GPU helps with everything. Web applications, databases and most business logic gain nothing from a graphics card. Renting a GPU server makes sense when your workload actually uses CUDA: machine learning, rendering, video encoding, or scientific computing.

What a server with a graphics card costs

The price is driven almost entirely by the card. An entry-level RTX server starts at a few hundred dollars a month; a professional configuration with 96 GB of VRAM costs several times that. CPU, memory and storage shift the total far less than the GPU does.

Compared with buying hardware outright, renting removes the upfront cost and the risk of the card becoming obsolete. A new NVIDIA generation ships roughly every two years, and a purchased card loses value with it. Renting also means someone else handles the failed PSU at three in the morning.

Choosing a configuration for neural networks

Start with video memory. A model that does not fit in VRAM will not run, regardless of how fast the card is. Quantisation reduces the requirement — 4-bit and 8-bit formats cut memory use substantially at some cost in quality — but there is a floor below which a given model simply will not load.

Context length and batch size matter too. A long context inflates the KV cache, and on a card with modest VRAM that becomes the binding constraint before the model weights do. If you are unsure, describe the model and framework to support and we will tell you which card fits.

GPU hosting for business

The most common reason companies move off hosted AI APIs is data. Sending customer records, medical data or internal documents to a third-party endpoint is often incompatible with an NDA or with GDPR. Self-hosted inference on a dedicated server keeps everything inside your own perimeter.

The second reason is cost at volume. Per-token pricing is convenient at low usage and expensive at scale; a fixed monthly server becomes cheaper past a certain request volume. Where that break-even sits depends on the model and the traffic, and it is worth calculating before committing either way.