AI performance
24 GB
total VRAM
2× 12 GB
64 GB
RAM
for offload and data
2×
graphics cards
RTX 3060 · concurrent models
A build for models up to ~30 billion parameters in 4-bit — the class most company document assistants run in today.
What runs on this build (4-bit, 8k context)
| Model | Memory | Speed |
|---|---|---|
Qwen2.5 14B balanced business assistant, RAG over documents | Fits10.5 GB | ~26 tok/s |
gpt-oss 20B (OpenAI) OpenAI open-weight model, fast thanks to MoE | Fits13 GB | ~83 tok/s |
Mistral Small 3.1 24B European model, strong on documents and instructions | Fits15.7 GB | ~16 tok/s |
Gemma 3 27B strongest Gemma, text and images | Fits17.1 GB | ~14 tok/s |
Qwen3 30B-A3B (MoE) big-model knowledge at small-model speed | Fits19.1 GB | ~91 tok/s |
Qwen2.5 32B demanding writing and analysis | Tight21.8 GB | ~12 tok/s |
Llama 3.3 70B flagship class, needs 48 GB of VRAM | Does not fit45 GB | — |
Memory is computed from model weights and KV cache. Speed is a rough estimate from the graphics memory bandwidth; measured burn-in values are added over time.
A computer built for one job: running large language models inside the company. Two RTX 3060 cards add up to 24 GB of memory, enough for 4-bit quantised models up to roughly 30 billion parameters — Qwen2.5 14B and 32B, Gemma 3 27B, Mistral Small 24B or OpenAI's gpt-oss 20B. The second card also lets you run two models at once: an assistant for the team and a second one processing documents in the background.
64 GB of RAM handles offloading of larger models and data work; the 2 TB WD Black SN850X NVMe loads a 20 GB model in seconds. The 1200 W Gold power supply leaves headroom for swapping in stronger cards later. Three industrial Noctua fans keep temperatures in check through hours of continuous load — this is a machine for a server room or utility room, not for a desk next to people. A quieter cooling variant is available for offices.
What it is for: running finished models (Ollama, LM Studio, vLLM), an assistant over company documents (RAG), several concurrent users, fine-tuning smaller models with LoRA. What it is not for: full training of large models — that needs 48 GB cards and a fast interconnect. The second card sits in a PCIe 4.0 x4 slot; for inference that does not matter since weights load once, but it would bottleneck tensor-parallel training. And two cards add up memory, not the speed of a single answer.
For an extra CZK 5,000 we swap the Ryzen 5 5600 for the sixteen-core Ryzen 9 5950X. Worth it if you will process data in parallel, serve more users or fine-tune; it does not speed up the answer generation itself, which runs on the GPUs.
Photos are illustrative.
We aim to supply exactly the part shown in the photo. In rare cases, for components without a named manufacturer (memory), we may supply the same model from a different manufacturer – with identical specifications, performance and warranty. Colour and style are always kept: a white build gets a white card. Where the manufacturer is named in the configuration, we supply exactly that model.
Want the exact models confirmed before you order? Message us and we will confirm them: WhatsApp · contact form
What's in the box and how we handle servicePacked PC, power cable and set-up guide · component boxes with pickup · service by phone and remotely
In the box
- Assembled and tested PC, packed for transport
- Power cable
- Printed first start-up guide – how to connect the PC and what to do after switching it on (download PDF)
- With in-store pickup, the original component boxes (warranty cards, manuals, accessories)
- When shipped, the component boxes can be added for €11–13 – option in the cart
Service even if you are not from Olomouc
Every build is stress-tested before it leaves us, so warranty claims are rare. If anything happens anyway: call us first and our technician tries to solve it over the phone – that is usually enough. If we need to see the PC, we send you a Zásilkovna code or a DPD label, you hand over the parcel and we take it into our Olomouc workshop with priority and ship it back after the repair. From Olomouc and nearby, just drop by – we fix it while you wait or by the next day.
Manufacturer and product safetyManufacturer: Erelen s.r.o., Šlechtitelů 813/21, Holice, 779 00 Olomouc, Czech Republic · obchod@erelen.cz · www.erelen.cz
Product identifier: AI PC – 2× RTX 3060 12 GB · 24 GB VRAM · 64 GB RAM (ai-pc-2x-rtx-3060-24gb-vram-ryzen-5600)
Safety: The PC is intended for dry indoor use. Do not cover the vents, keep it away from heat sources and water, and disconnect it from the mains before opening the case. Manuals and safety instructions for the components are included in the box or sent on request.
LOCAL AI PC
AI PC – 2× RTX 3060 12 GB · 24 GB VRAM · 64 GB RAM
24 GB of VRAM across two cards: a company document assistant up to 30B parameters. Data stays with you.
Other
Microsoft Office
Warranty
Total Price
€2450€2025 excl. VAT
ASUS gaming gear
Bundle price with a PC onlyThe set is a separate item on your order and invoice. New goods, 24-month warranty.
Monitor for this PC
In stock · ships with the PC