OwnAI Compute
Book a call Sign in
Enterprise AI infrastructure configurator

Design your private AI infrastructure

Step 1 of 11

1 · Organisation size

How many employee accounts will the environment serve? This sets registered capacity; simultaneous users are estimated separately at the next steps.

AI capacity dashboard

Meets workload
Employee accounts50
Recommended concurrent users15 (30% at peak)
GPUs2 × GeForce RTX 5090
GPU memory64 GB aggregate
Supported modelsLlama 3.2 3B, Llama 3.1 8B, Gemma 3 12B, Qwen2.5 14B, Qwen2.5 32B
Estimated throughput4,398 tokens/s (theoretical max 11,756)
Daily token capacity85.51 M vs demand 350 k generated
Monthly token capacity1.88 bn
DeploymentOn-Premises Private AI Data Centre

Illustrative until validated by benchmarking: Llama 3.1 8B, Int4, 8,192-token context, batching to 15 concurrent sequences.

Rejoining the server...

Rejoin failed... trying again in seconds.

Failed to rejoin.
Please retry or reload the page.

The session has been paused by the server.

Failed to resume the session.
Please retry or reload the page.