# Dynamics NAV AI Assistant Sizing and Value Calculator

> Source: https://netray.co/tools/dynamics-nav-ai-assistant-sizing-and-value-calculator
> Publisher: Netray (netray.co), AI and integration engineering for ERP and manufacturing systems.
> Section: Free Tools

## Short answer

Work out the GPUs, index size and monthly value of a private AI assistant on NAV from your users and question volume.

## Category

on-prem-ai

## Erp

Microsoft Dynamics NAV

## Audience

- CIO
- IT manager
- NAV administrator
- Finance

## Tool

**Kind:** calculator

**Currency:** $

**Inputs:**

#### Named NAV users

**Key:** users

**Type:** number

**Default:** 90

**Min:** 1

**Step:** 10

**Unit:** users

#### Share active on a given day

**Key:** dau_pct

**Type:** slider

**Default:** 35

**Min:** 5

**Max:** 100

**Step:** 5

**Unit:** %

#### Questions per active user per day

**Key:** q_per_user

**Type:** number

**Default:** 8

**Min:** 1

**Step:** 1

**Unit:** questions

#### Prompt plus answer tokens per question

**Key:** tokens_per_q

**Type:** number

**Default:** 3000

**Min:** 200

**Step:** 100

**Unit:** tokens

#### Documents to index

**Key:** docs

**Type:** number

**Default:** 80000

**Min:** 0

**Step:** 5000

**Unit:** documents

#### Average pages per document

**Key:** pages

**Type:** number

**Default:** 3

**Min:** 1

**Step:** 1

**Unit:** pages

#### Minutes saved per question

**Key:** mins_saved

**Type:** number

**Default:** 5

**Min:** 0

**Step:** 1

**Unit:** min

#### Loaded hourly cost

**Key:** hourly

**Type:** number

**Default:** 38

**Min:** 0

**Step:** 1

**Unit:** per hour

#### GPU monthly cost

**Key:** gpu_month

**Type:** number

**Default:** 1800

**Min:** 0

**Step:** 100

**Unit:** per GPU

#### Sustained tokens per second per GPU

**Key:** tps_gpu

**Type:** number

**Default:** 1200

**Min:** 100

**Step:** 100

**Unit:** tokens/s

**Help:** Measured aggregate throughput for your model on your card.

#### One-time build cost

**Key:** build_cost

**Type:** number

**Default:** 45000

**Min:** 0

**Step:** 5000

**Unit:** one-time

**Outputs:**

#### Daily active users

**Key:** active

**Expr:** users * dau_pct / 100

**Format:** decimal

#### Questions per day

**Key:** q_day

**Expr:** active * q_per_user

**Format:** integer

#### Tokens per day

**Key:** tokens_day

**Expr:** q_day * tokens_per_q

**Format:** integer

#### Peak concurrent requests

**Key:** peak_conc

**Expr:** q_day * 0.2 / 3600 * 20

**Format:** decimal

**Description:** 20% of daily questions in the busiest hour, about 20 seconds per request.

#### GPUs needed (before redundancy)

**Key:** gpus

**Expr:** max(1, ceil(q_day * 0.2 * tokens_per_q / 3600 / tps_gpu))

**Format:** integer

**Primary:** true

#### Retrieval index size

**Key:** index_gb

**Expr:** docs * pages * 2 * 4096 * 1.5 / 1000000000

**Format:** decimal

**Description:** Two chunks per page, 4096 bytes per vector, 50% overhead.

#### Hours saved per month

**Key:** hours_month

**Expr:** q_day * 22 * mins_saved / 60

**Format:** hours

#### Monthly value of time saved

**Key:** value

**Expr:** hours_month * hourly

**Format:** currency

#### Monthly net value after GPU cost

**Key:** net

**Expr:** value - gpus * gpu_month

**Format:** currency

**Primary:** true

#### Simple payback

**Key:** payback

**Expr:** if(gt(net, 0), build_cost / net, 0)

**Format:** months

**Chart:**

#### GPUs needed vs questions per active user

**Type:** bar

**X:** q_per_user

**From:** 2

**To:** 60

**Steps:** 20

**Series:**

- gpus

**Disclaimer:** Planning estimate only. Measure throughput on your own hardware, add redundancy for production and validate time savings in a pilot.

## Content

**Intro:** 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.

**Sections:**

#### How to use it

**Body:** 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.

**Bullets:**

- Test two or three throughput values
- Use the chart to see GPU steps
- Keep time saved conservative
- Share the export with finance

#### The formulas

**Body:** 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

**Body:** 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.

**Cta:** If you want the inputs reviewed against your NAV environment, Netray can run a short sizing session with your IT team.

**Faq:**

#### Why use a bar chart?

**Answer:** 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?

**Answer:** 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?

**Answer:** 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?

**Answer:** No. It covers GPU cost and one-time build cost only. Add operating labour and licences for a full total cost view.

## Search terms

NAV AI sizing calculator, on-prem LLM sizing, AI assistant ROI NAV, GPU count for LLM users, private AI payback calculator, retrieval index size calculator

---
Talk to an engineer: https://netray.co/contact?intent=erp_ai | Machine catalog: https://netray.co/agent/catalog.json