# Macola AI Assistant Sizing and Value Calculator

> Source: https://netray.co/tools/macola-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 Macola.

## Category

on-prem-ai

## Erp

Exact Macola

## Audience

- CIO
- IT manager
- Finance controller
- ERP consultant

## Tool

**Kind:** calculator

**Currency:** $

**Inputs:**

#### Named users

**Key:** users

**Type:** number

**Default:** 60

**Min:** 1

**Step:** 5

**Unit:** users

**Help:** Licensed or named Macola 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:** 20000

**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:** 38

**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:** 45000

**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 estimates GPU count, token volume, document index size, hours saved and payback for a private AI assistant on Macola. Change the inputs to match your user base and see the chart for how cost and value scale with users.

**Sections:**

#### How to use the calculator

**Body:** Enter named Macola users and the share who actually use the assistant on a typical day, then how many questions each asks and how many tokens a question and answer consume together. Add the number and length of documents you plan to index, the minutes each answer saves and your loaded hourly cost. The outputs give peak concurrent requests, a GPU estimate with and without a standby, the index size and a simple monthly value.

#### Formulas and assumptions

**Body:** Questions per day are active users times questions each. The busiest hour is assumed to carry 25 percent of daily questions and each answer to take 20 seconds, which sets peak concurrency. Load in tokens per second is the larger of concurrency times 40 tokens per second per stream and busy-hour tokens divided by 3600. GPUs needed are the larger of the GPUs required to hold the model and load divided by the throughput per GPU you enter. Index size assumes 2 chunks per page and about 6 KB per chunk including vectors and metadata. A month is 21 working days.

#### Reading the result

**Body:** For a Macola-sized user base the GPU count is usually driven by the model's memory footprint, not by user load, so the estimate often lands at one or two cards. Value depends almost entirely on minutes saved per question, which is the number to test with a pilot. If payback shows zero, the monthly value does not cover the monthly GPU cost under your inputs.

**Cta:** If you want these numbers tested against your real Macola usage, Netray can help run a small pilot. The calculator is free either way.

**Faq:**

#### Why is the GPU count so low?

**Answer:** A few dozen active users generate light load. The count is usually set by how many GPUs are needed to hold the model, so a single card or a pair is common. Larger models or many more users change this.

#### What throughput per GPU should I enter?

**Answer:** It depends on model, quantisation and batching. A figure from 800 to 2500 aggregate tokens per second is a plausible range for mid-size models, but measure on your own hardware before committing.

#### How reliable is minutes saved?

**Answer:** It is the least certain input. Use a small pilot to time how long a lookup takes today versus with the assistant, then enter the measured average.

#### Does it include setup costs?

**Answer:** Payback uses the one-time setup cost you enter, divided by monthly value minus GPU running cost. It excludes licences you may already own and staff time beyond what you include in setup.

## Search terms

Macola AI cost, Macola 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