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 | 250 |
|---|---|
| Recommended concurrent users | 50 (20% at peak) |
| GPUs | 4 × RTX PRO 6000 Blackwell Server Edition |
| GPU memory | 384 GB aggregate |
| Supported models | Llama 3.2 3B, Llama 3.1 8B, Gemma 3 12B, Qwen2.5 14B, Qwen2.5 32B, Llama 3.3 70B, gpt-oss 120B (MoE, 5B active), Llama 3.1 405B |
| Estimated throughput | 5,358 tokens/s (theoretical max 6,951) |
| Daily token capacity | 104.16 M vs demand 1.75 M generated |
| Monthly token capacity | 2.29 bn |
| Deployment | Private AI Infrastructure · Dedicated Deployment |
Illustrative until validated by benchmarking: Qwen2.5 32B, Int4, 8,192-token context, batching to 50 concurrent sequences.