Start small. Prove it.
Scale when it’s earned.
The Dell Pro Max with GB10 is the entry point of the Dell × NVIDIA ladder. Develop, test and validate on your desk — what you build here moves up the stack unchanged.
Services
Every service below runs on this box. Click Open — you never leave the portal.
Chat
On-device chat with the models served on this box. The service endpoint is configured by the portal operator; no calls are made from this surface.
Chat service is up on this box. Open the chat surface from the service endpoint configured for this deployment.
Images
Local image generation. The service endpoint is configured by the portal operator.
Image service is up on this box. Use the image service endpoint configured for this deployment.
Whisper
Local speech-to-text and transcription.
Whisper service is up on this box. Use the ASR endpoint configured for this deployment.
Monitor
Service and workload monitoring for this box.
Monitoring is available through the fleet dashboards. Open the monitor surface from the configured endpoint.
Plan a Dell AI solution, POC to production
From a small proof of concept to supported production infrastructure — right-sized across Dell Pro Max, PowerEdge and Dell AI Factory.
Turn a model requirement into a Dell solution
Start with the customer outcome, separate POC from production, and show a credible path across Dell Pro Max, PowerEdge and Dell AI Factory.
RECOMMENDED DELL SOLUTION
Dell PowerEdge XE9780
Fits the selected workload with useful headroom.
More than the accelerator
Production readiness includes compute, data, network, protection, support and validation of the exact model-serving stack.
Where the capacity goes
Balanced for the workload
Show how the model feels on a Dell platform
Compare decode speed, prompt processing and multi-user throughput—then explain why the inference engine changes the result.
per user
How fast the answer appears
4–8Comfortable
12–25Fast
30–60Instant feel
60+
Compare deployment stages on the same job
Show where a Dell Pro Max POC stops and where PowerEdge production—or a rack-scale Dell AI Factory—starts.
| Dell system | Stage | Fit | Memory | Per-user speed | Power | Indicative capex | Best use |
|---|
Speed is a modeled range, not a vendor peak or guarantee. Production selection must also validate availability, HA, data, networking, security and support. Pricing remains editable in Cost.
Build the case for Dell on-premise AI
Compare acquisition, energy, support and residual value with an equivalent cloud service—without hiding editable assumptions.
—
—
36-month comparison
Tools
The calculator tools now live in the Planner, and the Dell 17G Spec Assistant is its own entry.
Dell Hardware
Dell system reference data used across the Planner. Every number is dated, source-linked and editable in one place.
| Dell system | Stage | Accelerators | Memory | Power | Best use |
|---|
Manage
Portal administration: services, model management and access policy. Contact: info@4rconsultancy.nl · linkedin.com/in/markvanaardenne.
Dell 17G Spec Assistant
Configure a PowerEdge 16G/17G generation system: choose the chassis, accelerators, memory, storage and services. This tool is standalone and unchanged by the Dell AI suite integration.