On-Prem AIFree calculatorPDF, Excel, Word exportMicrosoft Dynamics AX 2012

Dynamics AX 2012 AI Assistant Sizing and Value Calculator

Use this calculator to turn your AX 2012 user count and question volume into a GPU count, token load, index size and a simple payback. Every formula is shown so finance and IT can challenge the assumptions.

Your numbers

users
30 %
questions
tokens

Includes retrieved context. Document questions run higher than database lookups.

documents
pages
min
per hour
per GPU
tokens/s

Aggregate throughput with batching for your model and card. Measure it; do not trust a datasheet.

one-time

Your results

GPUs needed (before redundancy)
1
Peak-hour tokens per second divided by sustained tokens per second per GPU, minimum one.
Monthly value minus GPU cost
$31,064
Daily active users
54
Questions per day
540
Tokens per day
1,890,000
Questions per day times tokens per question.
Peak concurrent requests
0.6
Assumes 20% of daily questions land in the busiest hour and each takes about 20 seconds.
Retrieval index size
7.3728
Two chunks per page, 1024-dimension float32 vectors, 50% overhead for text and metadata.
Hours saved per month
792 hrs
Monthly value of time saved
$33,264
Simple payback
1.9 months
One-time cost divided by monthly net value. Zero means no payback at these inputs.

Planning estimate. Measure real throughput on your model and hardware, add redundancy for production, and treat time-saved figures as hypotheses until a pilot confirms them.

Save results:

Monthly net value vs named users

Sweeps Named AX users from 20 to 1000, holding your other inputs fixed.

Get a sizing review for your AX 2012 estate

Optional: share your inputs and we will sanity check GPU count, index design and rollout phases.

Optional. The tool and every export work without this. No spam.

How to use it

Enter named users and the share who actually use the assistant in a day. Estimate questions per user from the pilot or from how often people ask colleagues for data today. Tokens per question include retrieved context, so document-heavy use needs a larger number. Replace the default throughput with a figure measured on your own card.

  • Start with 20 to 30% daily active users
  • Use a measured tokens-per-second value
  • Add redundancy for production
  • Run low, expected and high scenarios

The formulas

Questions per day equals named users times active share times questions each. Peak-hour tokens per second equals 20% of daily questions times tokens per question divided by 3600. GPUs equal that peak divided by sustained throughput, rounded up. Index size multiplies pages by two chunks per page by 4096 bytes per vector with 50% overhead. Hours saved use 22 working days.

Reading the result

The GPU count is a floor for capacity, not a recommendation to run a single card in production. The payback figure is only as good as minutes saved per question, which is the weakest input; test it with a pilot group and timed tasks. If net value is negative at realistic inputs, a simpler tool such as reports or Power BI may serve you better.

Frequently Asked Questions

Why 20% of questions in the busiest hour?

It is a conservative planning assumption for office workloads where use clusters in the morning. Replace it with your own peak share if you have usage data.

Does throughput depend on the model?

Strongly. Model size, quantisation, context length and batch size all change tokens per second. Measure on the model you intend to run.

Why is the index so small?

Vectors are compact. Most storage in real deployments is the original documents, not the index, which this tool does not size.

Can I trust the payback number?

Treat it as a hypothesis. Time saved per question is an estimate and adoption varies. Validate with a pilot before committing budget.

If you want these numbers checked against your AX 2012 environment, Netray can run a short sizing review with your IT team.

Keep exploring

Free tools

ERP fixes and how-tos

AI on your ERP

Integrations

Software