Bare-Metal GPU Servers

NVIDIA RTX 6000 Ada — 48 GB per GPU for Rendering & AI

Two, four or eight NVIDIA RTX 6000 Ada Generation GPUs on bare metal: 48 GB of GDDR6 with ECC per card, 18,176 CUDA cores, 142 third-generation RT Cores and fourth-generation Tensor Cores with FP8. Dual Xeon Gold host with 384 GB RAM. No hypervisor. No setup fees.

See Pricing & Order

From €99/day (4 GPUs) · excl. VAT

ISO 27001 & NEN 7510 Certified Data Rooms Tier 3 Compliant Data Rooms 13+ Years on Market
6x FD Gazellen Award Winner
ISO 27001 & NEN 7510 Certified Data Rooms
Tier 3 Compliant Data Rooms
13+ Years on Market

Built for Rendering, AI & Simulation

One card for ray-traced rendering, AI training and inference: 48 GB of ECC memory per GPU and up to 384 GB per server

3D Rendering

GPU rendering in Blender Cycles, V-Ray, Redshift and Octane on 142 third-generation RT Cores per GPU. 48 GB per card holds heavy production scenes in GPU memory.

AI Training & Fine-Tuning

Fine-tune LLMs and diffusion models with PyTorch on fourth-generation Tensor Cores with FP8 support, scaled across up to eight GPUs with DeepSpeed or FSDP.

LLM Inference

Serve 70B-class models across several GPUs with vLLM, or run a separate model on each card for multi-tenant inference.

Video & Virtual Production

Encode and decode AV1, HEVC and H.264 in hardware on NVENC/NVDEC, and drive real-time scenes in Unreal Engine and NVIDIA Omniverse.

Simulation & Visualization

ECC-protected memory and 91 TFLOPS of FP32 per GPU for engineering simulation, CFD post-processing and scientific visualization.

Generative Media

Stable Diffusion, Flux and video models in ComfyUI, with 48 GB per GPU for large checkpoints and high-resolution batches.

Software Compatibility

Professional NVIDIA RTX drivers for the standard rendering, AI and video stack

CUDA 12
Toolkit & cuDNN
PyTorch
Deep Learning
TensorFlow
Machine Learning
vLLM
LLM Serving
Ollama
Local LLMs
DeepSpeed
Training Optimization
Transformers
Hugging Face
ComfyUI
Generative AI
Blender
3D Rendering
V-Ray
Rendering
Redshift
Rendering
OctaneRender
Rendering
Unreal Engine
Real-Time 3D
NVIDIA Omniverse
3D Collaboration
FFmpeg
NVENC Video

NVIDIA RTX 6000 Ada Server Pricing

No setup fees. No hidden costs. All prices exclude VAT.

Configuration GPU Memory RAM Storage Daily Weekly Monthly Per GPU/mo Status
4x RTX 6000 Ada 2x Xeon Gold 6226R 192 GB 384 GB 2000 GB NVMe €99 €550 €1,995 €499 Order
CPU
2x Intel® Xeon® Gold 6226R Processor 16C/32 3.9 GHz
RAM
384 GB
Storage
2000 GB NVMe
Network
1 Gbit
8x RTX 6000 Ada 2x Xeon Gold 6226R 384 GB 384 GB 2000 GB NVMe €165 €899 €3,290 €411 Order
CPU
2x Intel® Xeon® Gold 6226R Processor 16C/32 3.9 GHz
RAM
384 GB
Storage
2000 GB NVME
Network
1 Gbit
8x RTX 6000 Ada 2x Xeon Gold 6248R 384 GB 384 GB 2000 GB NVMe €175 €949 €3,490 €436 Order
CPU
2 x Intel® Xeon® Gold 6248R Processor 24C/48, 4.00 GHz
RAM
384 GB
Storage
2000 GB NVME
Network
1 Gbit
2x RTX 6000 Ada 2x Xeon Gold 6226R, monthly only 96 GB 384 GB 2000 GB NVMe — — €1,060 €530 Order
CPU
2x Intel® Xeon® Gold 6226R Processor 16C/32 3.9 GHz
RAM
384 GB
Storage
2000 GB NVME
Network
1 Gbit

Why LeaderGPU

Trusted by researchers and enterprises across Europe

Bare-Metal Performance

No hypervisor, no virtualization overhead. Direct hardware access for maximum GPU throughput.

Ready in 1 Business Day

Your server is provisioned within 1 business day of your order, with no setup fees and no hypervisor.

Tier 3 Compliant Data Rooms

Enterprise-grade data rooms with ISO 27001 and NEN 7510 certification.

Flexible Billing

Daily, weekly or monthly rental, the 2x configuration by the month. No setup fees. Scale your commitment to match your project timeline.

13+ Years / 6x FD Gazellen

Operating since 2012. Among only 78 companies to receive the FD Gazellen award in 2024.

Enterprise Connectivity

Peering via AMS-IX and NL-ix. Four redundant internet connections for maximum uptime.

Data Room Infrastructure

Netherlands-based Tier 3 compliant data rooms with enterprise-grade redundancy

  • Tier 3 compliant data rooms supplier
  • ISO 27001 and NEN 7510 data room standards
  • Each server connected to dual-power feeds (UPS)
  • Generators: N+1
  • Stable 24°C cooling, backup units (N+1)
  • Four redundant internet connections with peering via NL-ix and AMS-IX
  • VESDA very early smoke detection + gas fire extinguishing
  • 24/7 security guards, fingerprint scanners, CCTV, intrusion detection

Supported Operating Systems

Ubuntu 22.04 LTS
Ubuntu 24.04 LTS
Custom OS (1 business day)
24/7 Support

Ordering & incidents around the clock. Technical support Mon-Fri, 9:00-18:00 CET.

Frequently Asked Questions

How quickly will my server be provisioned?
Your server is provisioned within 1 business day of placing your order. A configuration that is busy shows the date it is available from in the pricing table.
How much GPU memory does the RTX 6000 Ada have?
Each RTX 6000 Ada Generation carries 48 GB of GDDR6 with ECC and 960 GB/s of bandwidth: 96 GB across a 2-GPU server, 192 GB across a 4-GPU server and 384 GB across an 8-GPU server. ECC protects long renders and training runs from silent memory errors.
How does the RTX 6000 Ada compare with the RTX A6000?
Both have 48 GB of GDDR6 with ECC. The RTX 6000 Ada is the Ada Lovelace successor: 18,176 CUDA cores against 10,752, third-generation RT Cores, fourth-generation Tensor Cores with FP8 support, and more than twice the FP32 throughput.
Which configurations are available?
Four: 4x RTX 6000 Ada with two Xeon Gold 6226R (16 cores each), 8x RTX 6000 Ada with two Xeon Gold 6226R, 8x RTX 6000 Ada with two Xeon Gold 6248R (24 cores each), and 2x RTX 6000 Ada with two Xeon Gold 6226R, rented by the month only. All four have 384 GB of system RAM and 2000 GB of NVMe storage.
Is there NVLink between the GPUs?
No. The RTX 6000 Ada does not support NVLink, so the GPUs communicate over PCIe. PyTorch DDP, DeepSpeed and tensor parallelism in vLLM work over PCIe, and rendering engines use each GPU independently.
Are there any setup fees?
No. There are zero setup fees for any rental period — daily, weekly, or monthly. You only pay the rental price listed. All prices are exclusive of VAT.
Which operating systems are supported?
RTX 6000 Ada servers ship with Ubuntu 22.04 LTS or Ubuntu 24.04 LTS. Custom OS installations are available on request and require 1 business day. All servers come with root access so you have full control over the software stack.
Where are the servers located?
Our servers are hosted in Tier 3 compliant data rooms in the Netherlands, upheld to ISO 27001 and NEN 7510 standards, with peering via AMS-IX and NL-ix for excellent European and global connectivity.
Trusted & Secure

Payment Options

All transactions are processed via PCI-DSS compliant gateways. SEPA bank transfer also available for EU customers.

Start Rendering on NVIDIA RTX 6000 Ada

48 GB per GPU on bare metal. 2, 4 or 8 GPUs. No setup fees.

See Pricing & Order View All GPU Servers