# Made2Manage AI Assistant Sizing and Value Calculator

> Source: https://netray.co/tools/made2manage-ai-assistant-sizing-and-value-calculator
> Publisher: Netray (netray.co), AI and integration engineering for ERP and manufacturing systems.
> Section: Free Tools

## Short answer

Estimate GPU count, token volume, index size, hours saved and payback for a private on-prem AI assistant on Made2Manage.

## Category

on-prem-ai

## Erp

Aptean Made2Manage

## Audience

- CIO
- IT manager
- Finance controller
- ERP consultant

## Tool

**Kind:** calculator

**Currency:** $

**Inputs:**

#### Named users

**Key:** users

**Type:** number

**Default:** 45

**Min:** 1

**Step:** 5

**Unit:** users

**Help:** Licensed or named Made2Manage users who could use the assistant.

#### Share active on a typical day

**Key:** active

**Type:** slider

**Default:** 40

**Min:** 5

**Max:** 100

**Step:** 5

**Unit:** %

**Help:** Percent of named users who ask at least one question per day.

#### Questions per active user per day

**Key:** q

**Type:** number

**Default:** 6

**Min:** 1

**Step:** 1

**Unit:** questions

#### Average prompt plus answer size

**Key:** tokens

**Type:** number

**Default:** 1800

**Min:** 200

**Step:** 100

**Unit:** tokens

**Help:** Include retrieved context. Typical range 1000 to 3000.

#### Documents to index

**Key:** docs

**Type:** number

**Default:** 15000

**Min:** 0

**Step:** 1000

**Unit:** documents

#### Average pages per document

**Key:** pages

**Type:** number

**Default:** 4

**Min:** 1

**Step:** 1

**Unit:** pages

#### Minutes saved per question

**Key:** mins

**Type:** number

**Default:** 4

**Min:** 0

**Step:** 0.5

**Unit:** minutes

**Help:** Measure in a pilot; this is the most uncertain input.

#### Loaded hourly cost

**Key:** rate

**Type:** number

**Default:** 36

**Min:** 0

**Step:** 1

**Unit:** per hour

#### GPU monthly cost

**Key:** gpucost

**Type:** number

**Default:** 1800

**Min:** 0

**Step:** 100

**Unit:** per GPU per month

**Help:** Amortised purchase plus power, space and support, or a private cloud rate.

#### Aggregate tokens per second per GPU

**Key:** tps

**Type:** number

**Default:** 1500

**Min:** 100

**Step:** 100

**Unit:** tokens/s

**Help:** Assumption: depends on model, quantisation and batching. Measure on your hardware.

#### GPUs needed to hold the model

**Key:** modelgpus

**Type:** select

**Default:** 1

**Options:**

##### 1 GPU

**Value:** 1

##### 2 GPUs

**Value:** 2

##### 4 GPUs

**Value:** 4

#### One-time setup cost

**Key:** setup

**Type:** number

**Default:** 40000

**Min:** 0

**Step:** 1000

**Unit:** once

**Help:** Integration, indexing, testing and rollout effort.

**Outputs:**

#### Active users per day

**Key:** active_users

**Expr:** users * active / 100

**Format:** integer

#### Questions per day

**Key:** q_day

**Expr:** active_users * q

**Format:** integer

#### Tokens per day

**Key:** tok_day

**Expr:** q_day * tokens

**Format:** integer

**Description:** Questions per day times average tokens per question.

#### Peak concurrent requests

**Key:** peak_conc

**Expr:** max(1, ceil(q_day * 0.25 / 3600 * 20))

**Format:** integer

**Description:** Assumes 25% of daily questions in the busiest hour and 20 seconds per answer.

#### Peak load

**Key:** load_tps

**Expr:** max(peak_conc * 40, tok_day * 0.25 / 3600)

**Format:** integer

**Description:** Tokens per second: the larger of 40 tokens/s per concurrent stream and busy-hour token volume.

#### GPUs needed

**Key:** gpus

**Expr:** max(modelgpus, ceil(load_tps / tps))

**Format:** integer

**Primary:** true

**Description:** Larger of the GPUs needed to hold the model and load divided by throughput per GPU.

#### GPUs with a standby replica

**Key:** gpus_ha

**Expr:** gpus + modelgpus

**Format:** integer

**Description:** Adds one more model replica for resilience.

#### Vector index size

**Key:** index_gb

**Expr:** docs * pages * 2 * 6 / 1000000

**Format:** decimal

**Description:** GB, assuming 2 chunks per page and about 6 KB per chunk including vectors and metadata.

#### Hours saved per month

**Key:** hours

**Expr:** q_day * 21 * mins / 60

**Format:** hours

**Description:** 21 working days per month.

#### Monthly value

**Key:** value

**Expr:** hours * rate

**Format:** currency

#### Monthly GPU cost (with standby)

**Key:** cost

**Expr:** gpus_ha * gpucost

**Format:** currency

#### Net monthly value

**Key:** net

**Expr:** value - cost

**Format:** currency

**Primary:** true

#### Simple payback

**Key:** payback

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

**Format:** months

**Description:** Setup cost divided by net monthly value. Zero means value does not cover running cost.

**Chart:**

#### Monthly value vs GPU cost by named users

**Type:** line

**X:** users

**From:** 10

**To:** 1000

**Steps:** 25

**Series:**

- value
- cost

**Disclaimer:** Planning estimate. Throughput, minutes saved and token counts vary widely; measure them in a pilot before committing budget.

## Content

**Intro:** This free calculator sizes a private AI assistant for a Made2Manage shop: peak load, GPU count, index size, hours saved and payback. Adjust the inputs and read the chart to see how value and cost change with user count.

**Sections:**

#### How to use the calculator

**Body:** Set the number of Made2Manage named users and the share who use the assistant daily. Enter how many questions each asks, the tokens per question and answer, and the documents you will index, such as travelers and inspection records. Then add minutes saved per answer, loaded hourly cost, the monthly cost of a GPU and a one-time setup cost. Outputs show load, GPUs, index size, value and payback.

#### Formulas and assumptions

**Body:** Active users equal named users times the active share. Questions per day multiply by questions per user. Peak concurrency assumes 25 percent of daily questions in the busiest hour and 20 seconds per answer. Token load takes the larger of concurrency times 40 tokens per second and busy-hour tokens per second. GPUs equal the larger of the GPUs needed for the model and load divided by your throughput per GPU. The standby adds one model replica. Index size uses 2 chunks per page at about 6 KB each. A month is 21 working days.

#### Reading the result

**Body:** Small shops usually need one or two GPUs, set by the model size rather than by traffic. The value figure is a simple time saving, so check it with a pilot: time five common lookups before and after. If payback shows zero, monthly value is below monthly GPU cost for the inputs given.

**Cta:** If you want these estimates validated against your own Made2Manage usage, Netray can help scope a short pilot. The calculator needs nothing from us.

**Faq:**

#### What counts as a question?

**Answer:** One user prompt that triggers a lookup or an answer. A back-and-forth conversation of five turns counts as five. Use your own pilot data if you have it.

#### How do I choose tokens per question?

**Answer:** Include the prompt, retrieved context and answer. A lookup with a few rows and a short answer is often around 1000 to 2500 tokens. Document questions with long context can be higher.

#### Why include a standby?

**Answer:** A single GPU is a single point of failure. The standby output adds a second replica so the assistant stays available during maintenance or a hardware fault.

#### Is the value realistic?

**Answer:** It is only as good as minutes saved and the share of users active. Treat it as a hypothesis to measure, not a promise.

## Search terms

Made2Manage AI cost, Made2Manage AI ROI calculator, on-prem LLM GPU sizing calculator, private AI assistant payback, ERP AI sizing tool, GPU count for LLM users, vector index size estimate

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