Dynamics NAV AI Assistant Sizing and Value Calculator
This calculator sizes a private AI assistant for Dynamics NAV from your user count and expected question volume. It outputs GPUs, token load, retrieval index size, hours saved and a simple payback, and every formula is visible.
Your numbers
Measured aggregate throughput for your model on your card.
Your results
Planning estimate only. Measure throughput on your own hardware, add redundancy for production and validate time savings in a pilot.
GPUs needed vs questions per active user
Sweeps Questions per active user per day from 2 to 60, holding your other inputs fixed.
Get a sizing review for your NAV estate
Optional: share your inputs and we will sanity check the GPU count and rollout assumptions.
Optional. The tool and every export work without this. No spam.
How to use it
Set named users and the share who use the assistant on a typical day. Questions per user is the key driver; use the number of data requests people send to colleagues or run through SmartList-style workarounds today. Adjust tokens per question upward if answers cite documents. Enter a throughput you measured, not a marketing number.
- Test two or three throughput values
- Use the chart to see GPU steps
- Keep time saved conservative
- Share the export with finance
The formulas
Questions per day equal active users times questions each. Peak-hour tokens per second equal 20% of daily questions times tokens per question divided by 3600. GPUs equal that peak divided by per-GPU throughput, rounded up with a minimum of one. Value equals hours saved times loaded hourly cost, using 22 working days, minus GPU cost.
Reading the result
GPU count moves in steps, so the chart is a bar chart: a small rise in questions can add a card. Index size is modest for most NAV estates; model memory is the larger hardware driver. A negative net value means the case rests on factors outside this model, or that a simpler tool is a better fit.
Frequently Asked Questions
Why use a bar chart?
GPU count is a whole number that jumps when load crosses a capacity step. A bar chart shows those steps more honestly than a smooth line.
Is one GPU enough for production?
Often for small estates, but production usually wants redundancy or a fallback path. Decide based on how critical the assistant becomes.
How do I estimate minutes saved?
Time five typical tasks with and without the assistant in a pilot. Use the median, not the best case.
Does it include licences and staff time?
No. It covers GPU cost and one-time build cost only. Add operating labour and licences for a full total cost view.
If you want the inputs reviewed against your NAV environment, Netray can run a short sizing session with your IT team.
Related Tools
Dynamics NAV Private AI Layer Blueprint Generator
Describe your NAV environment and get a shareable plan for a private AI assistant: components, security controls, 3-phase rollout and open questions.
On-Prem AIGPU Sizing Calculator for LLM Inference
Work out how many GPUs you need to serve a given open-weight model to your user base, based on memory footprint and token throughput.
On-Prem AIOn-Prem LLM Total Cost of Ownership Calculator
Model the full multi-year cost of running LLMs on your own hardware, including GPU capex, power, cooling, support contracts, and operations staffing.
On-Prem AILLM Inference Cost Per Million Tokens Calculator
Convert GPU hourly cost, cluster throughput, and real-world utilization into a defensible self-hosted cost per million tokens, exposing what idle GPU time actually costs you.
More On-Prem AI tools
See allKeep exploring
Free tools
- Dynamics GP AI Assistant Sizing and Value CalculatorSize a private AI assistant for Dynamics GP: GPUs, index and monthly value from users and questions per day.
- Business Central On-Prem AI Assistant Sizing and Value CalculatorSize GPUs, index and monthly value for a private AI assistant on Business Central on-prem from user and question volumes.
- Dynamics NAV Private AI Layer Blueprint GeneratorDescribe your NAV environment and get a shareable plan for a private AI assistant: components, security controls, 3-phase rollout and open questions.
ERP fixes and how-tos
- Adding a Private AI Layer to Dynamics NAV On-PremAdd AI to Dynamics NAV on-prem without moving data: SQL replica, web services, retrieval index, local LLM, mirrored NAV permission sets, approved write-back.
- Business Central Upgrade Path: From NAV and Older BC Versions to CurrentBusiness Central upgrade paths explained: NAV to BC 14, BC 14 to later versions, the data upgrade sequence and cloud migration as an alternative.
AI on your ERP
- AI for Dynamics GP and NAV, Before the Business Central DecisionDynamics GP mainstream support is ending and NAV is long retired from active development. Add a private LLM over GP or NAV data now, on-prem, without a forced Business Central move.
- AI for Dynamics NAV 2009-2018, before or instead of a Business Central migrationAdd AI to Dynamics NAV 2009-2018 without a Business Central migration: ground an LLM on C/AL tables through SQL Server, on-prem or private cloud.
Integrations
- How to add an AI chatbot to Microsoft Dynamics NAVAdd an AI chatbot to Dynamics NAV that answers from live item, order and BOM data, runs fully on-prem with open models, and respects NAV permissions and audit needs.
- How to add AI agents to Microsoft Dynamics NAVHow to add AI agents to Microsoft Dynamics NAV: a tool layer over NAV web services or SQL, human approval before writes, and on-prem models for legacy installs.