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 accounts | 50 |
|---|---|
| Recommended concurrent users | 15 (30% at peak) |
| GPUs | 2 × GeForce RTX 5090 |
| GPU memory | 64 GB aggregate |
| Supported models | Llama 3.2 3B, Llama 3.1 8B, Gemma 3 12B, Qwen2.5 14B, Qwen2.5 32B |
| Estimated throughput | 4,398 tokens/s (theoretical max 11,756) |
| Daily token capacity | 85.51 M vs demand 350 k generated |
| Monthly token capacity | 1.88 bn |
| Deployment | On-Premises Private AI Data Centre |
Illustrative until validated by benchmarking: Llama 3.1 8B, Int4, 8,192-token context, batching to 15 concurrent sequences.