On-premise AI scales flexibly and step by step: you can scale horizontally (add more servers) or scale vertically (more powerful GPUs). The onprem.ai software manages all systems centrally and distributes the load automatically.
Scaling strategies
Scale horizontally (more servers)
Advantage:
- Add capacity with additional servers as needed
- No need to replace existing hardware
- Plan larger installations together as additional servers or custom clusters
Dell D1 with one GPU (96 GB VRAM) and D2 with two GPUs (192 GB VRAM) are rack alternatives to S1 and S2, not larger successors. Both use the Dell PowerEdge R770 in a 2U rack chassis.
All configurations at a glance: server page
Scale vertically (more powerful GPUs)
Advantage:
- Higher performance and more memory per server
- Less management overhead
The software supports the full NVIDIA spectrum from the RTX PRO 6000 Blackwell up to the data center GPUs H100, H200, and GH200. Details on supported GPUs: software page
Hybrid approach
Combination:
- Base servers for standard workloads
- High-performance servers for critical applications
- Central management via the onprem.ai software
Scaling without data loss
Advantages of the modular architecture:
- Servers can be added without changing existing configurations
- Models remain available on all servers
- No data migration required
- Rolling updates without downtime, self-healing on failures
Costs when scaling
On-premise:
- Additional hardware only when needed
- No usage dependency, predictable costs
Cloud:
- Every additional user means more token costs
- Unpredictable bills
The more users, the faster your own hardware pays for itself. The cost calculator estimates costs, break-even, and residual value over three years on an S2 basis. Dell capacity is not calculated. Published prices for Dell D1 and D2 are on the pricing page. All prices and cost estimates are non-binding, excluding VAT.
Next steps
- Open the cost calculator and estimate costs on an S2 basis
- Contact us for individual scaling options
Sources and further information:
- Start small and scale (scaling strategies)
- On-premise AI for SMEs (scaling and clusters)