PC Praha Genoa AI server with RTX Pro 6000 graphics cards

AI server PC Praha Genoa – EPYC 9004, up to 8 GPUs

4× RTX 5080 16 GB (64 GB VRAM) / 768 GB DDR5 ECC / 4 TB NVMe
1 632 090 Kč
Skip to product information
PC Praha Genoa AI server with RTX Pro 6000 graphics cards
  • PC Praha Genoa AI server with RTX Pro 6000 graphics cards
  • Genoa AI server – top view of the graphics cards
  • Genoa AI server – overall view
  • Genoa AI server – open case
AI server PC Praha Genoa – EPYC 9004, up to 8 GPUs

PC Praha · AI and GPU servers

AI server PC Praha Genoa – EPYC 9004, up to 8 GPUs

Specifications by configuration

Graphics cards
4–8 GPUs
Graphics memory
64–768 GB
Processor
AMD EPYC 9354
Memory
768 GB DDR5 ECC
Form factor
7U rack for 8 GPUs
1 348 835 Kč excl. VAT
1 632 090 Kč incl. 21% VAT
Graphics cards
RAM
Storage

Assembly and testing: usually 5–7 working days. We often have the server in stock and ship it straight away – we always confirm the date individually.

Graphics cards
RAM768 GB DDR5 ECC
Storage
  • 24-month warranty, claims handled directly by us
  • We help with configuration and software
  • We can run it in our data centre on request

What the build includes

Graphics cards
4× RTX 5080 16 GB 64 GB VRAM in total
Processor
EPYC 9354 · Genoa 32C
Motherboard
ASRock GENOAD8X-2T/BCM
Memory
12× 64 GB DDR5 ECC RDIMM 768 GB in total
Storage
4 TB NVMe
Power supply
4× 2000 W power supply, redundant
Chassis
7U rack for 8 GPUs
GPU risers
4× PCIe riser
Cooling
CPU cooler and server fans
Assembly
Assembly, OS installation and 72-hour stress test

The price above is for the complete server including assembly. We are happy to quote a different CPU, network card or chassis.

A server for large models on the modern AMD EPYC 9004 platform with DDR5 and PCIe 5.0. Four to eight graphics cards, 768 GB of ECC memory and redundant power in a 7U rack chassis.

Full description, video and specifications

Which models this build can run

The selected configuration has 64 GB of graphics memory (VRAM). It comfortably fits, for example, these open language models:

  • Llama 3.3 70B / Qwen3-72B48 GB
  • Seed-OSS-36B28 GB
  • DeepSeek-R2 32B24 GB
  • Qwen3-30B-A3B MoE20 GB
  • Gemma 3 27B18 GB
  • Mistral Small 3 24B14 GB
  • Qwen3-14B12 GB

The larger model Mistral Large 2 123B needs roughly 70 GB of VRAM.

Indicative estimate for quantised models (mostly Q4) with headroom for context. Actual memory needs depend on context length and the number of concurrent users.

What we take care of

  • Custom pre-installation

    We pre-install Linux, NVIDIA drivers, CUDA, Docker and the software for your workload (e.g. vLLM or Ollama) – you can start working as soon as you switch it on.

  • 72 hours under load

    Before handover every server runs at full load for 72 hours while we check stability, temperatures and ECC memory errors.

  • Service within 24/48 hours

    We keep key spare parts in stock in Prague. Service visits and part replacement within 24/48 hours.

  • Hosting in our data centre

    No server room? We place the server in our data centre, take care of power, cooling and connectivity, and you access it remotely.

How we work on AI servers

Description

We build AI server PC Praha Genoa on the AMD EPYC 9354 processor (32 cores, Zen 4) and the ASRock GENOAD8X-2T/BCM board. Twelve DDR5 ECC channels provide fast system memory for models that do not fit entirely into the graphics cards, and PCIe 5.0 makes full use of RTX 5090 and RTX Pro 6000 cards. It is our platform for the most demanding business deployments: large language models for dozens of users, reasoning and agents with long context, and high-quality video generation.

Configuration

Processor AMD EPYC 9354 (32 cores, Zen 4, SP5 socket)
Motherboard ASRock GENOAD8X-2T/BCM – PCIe 5.0, 2× 10 GbE
Graphics cards 4, 6 or 8× of your choice: RTX 5080, RTX 4090, RTX 5090, Intel Arc Pro B70, NVIDIA L4, NVIDIA L40 or RTX Pro 6000
Memory 768 GB DDR5 ECC (12 modules)
Storage NVMe 4 or 8 TB
Power supply redundant, for 24/7 operation
Chassis 7U rack for 8 cards

How much graphics memory you need

Graphics memory Example configuration What runs comfortably
64–128 GB 4× RTX 5080, 4× RTX 4090, 4× RTX 5090 Llama 3.3 70B, Qwen3.5-122B-A10B (MoE)
144–192 GB 6× RTX 4090, 6× RTX 5090, 4× L40, 8× L4 Qwen3-235B-A22B, GLM-4.6 355B (Q4)
256–384 GB 8× RTX 5090, 6–8× L40, 4× RTX Pro 6000 DeepSeek-V3.2 / R1 671B (Q2), Qwen3-Coder-480B, Kimi-K2 1T (1.58-bit)
576–768 GB 6–8× RTX Pro 6000 the largest open models with plenty of headroom for context and concurrent users

Model sizes are indicative (Q4 quantisation unless stated otherwise), based on our configurator. Actual memory requirements depend on context length and the number of concurrent users. For language models the memory of the cards adds up; image and video generation needs the whole model on a single card.

What you get

  • A server built from new components – we assemble and test it in Prague.
  • Pre-installed software for whatever you want to run on the server (e.g. Ubuntu, drivers and CUDA, Docker, vLLM, llama.cpp, Ollama, ComfyUI). It is ready to work as soon as you switch it on.
  • 72 hours of stress testing under full load before handover.
  • 24-month warranty. We keep spare parts in Prague and provide service intervention within 24/48 hours.
  • The server does not have to stand at your premises – you can keep it in our data centre (hosting) and we take care of power, cooling and connectivity.

Operation and installation

The server belongs in a rack or a server room with power and cooling for roughly 0.7 to 5.2 kW depending on the cards. We can add faster networking (25 to 400 GbE) for connecting to storage or other servers on request. We can also run the server in our data centre.

Frequently asked questions

Who is Genoa for?
For companies that want to run the largest open models or serve many users at once. We build six and eight RTX Pro 6000 cards precisely on this platform.
Why 768 GB of system memory?
The board has 12 DDR5 channels and we populate all of them – that way the memory runs fastest. Large RAM also helps when part of the model does not fit into the graphics cards.
What is the difference compared with Turin Dual?
Turin Dual has two newer EPYC 9005 processors, up to 1.5 TB of RAM and can take 16 RTX Pro 6000 cards. Genoa is single-processor and costs less.
Can I start with four cards and add more later?
Yes, the chassis is designed for eight cards. When expanding, we add cards, risers and, if needed, power supplies – get in touch and we will work it out.

Customer reviews

There are no reviews yet.

Only customers who bought the product from us can leave a review – we send them a review link by e-mail after the purchase.

More AI servers

View all