# Infor Factory Track AI assistant sizing and value calculator

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

## Short answer

Size the GPUs and estimate the monthly value and payback of an on-prem AI assistant for Infor Factory Track users.

## Category

mes-shop-floor

## Erp

Infor Factory Track

## Industry

Manufacturing

## Audience

- CIO
- IT manager
- Finance

## Tool

**Kind:** calculator

**Currency:** $

**Inputs:**

#### Named users

**Key:** users

**Type:** number

**Default:** 80

**Min:** 1

**Step:** 10

**Unit:** users

**Help:** People with a Infor Factory Track login who could use the assistant.

#### Daily active share

**Key:** dau_share

**Type:** slider

**Default:** 35

**Min:** 5

**Max:** 100

**Step:** 5

**Unit:** %

**Help:** Share of named users who use the assistant on a given day.

#### 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

**Help:** Include retrieved context. Retrieval-heavy questions often run 2,000 to 6,000.

#### Documents to index

**Key:** docs

**Type:** number

**Default:** 15000

**Min:** 0

**Step:** 1000

**Unit:** documents

#### Average pages per document

**Key:** pages_per_doc

**Type:** number

**Default:** 6

**Min:** 1

**Step:** 1

**Unit:** pages

#### Minutes saved per question

**Key:** min_saved

**Type:** number

**Default:** 4

**Min:** 0

**Step:** 0.5

**Unit:** min

#### Loaded hourly cost

**Key:** hourly_cost

**Type:** number

**Default:** 45

**Min:** 0

**Step:** 1

**Unit:** $/h

#### GPU monthly cost

**Key:** gpu_cost

**Type:** number

**Default:** 2500

**Min:** 0

**Step:** 100

**Unit:** $/GPU/month

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

#### Tokens per second per GPU

**Key:** tps_per_gpu

**Type:** number

**Default:** 1200

**Min:** 50

**Step:** 50

**Unit:** tokens/s

**Help:** Aggregate throughput under batching for your chosen model. Measure on your hardware.

#### One-time setup cost

**Key:** setup_cost

**Type:** number

**Default:** 45000

**Min:** 0

**Step:** 5000

**Unit:** $

**Help:** Integration, data dictionary, hardware purchase if not in monthly cost, testing.

**Outputs:**

#### Daily active users

**Key:** active_users

**Expr:** users * dau_share / 100

**Format:** integer

#### Questions per day

**Key:** q_day

**Expr:** active_users * q_per_user

**Format:** integer

#### Tokens per day

**Key:** tokens_day

**Expr:** q_day * tokens_per_q

**Format:** number

#### Peak requests per second

**Key:** peak_rps

**Expr:** q_day / (8 * 3600) * 4

**Format:** decimal

**Description:** Assumes an 8-hour working day and a peak at 4 times the average rate.

#### Peak concurrent requests

**Key:** peak_conc

**Expr:** max(1, ceil(peak_rps * tokens_per_q / 25))

**Format:** integer

**Description:** Assumes each request streams at about 25 tokens per second.

#### GPU count estimate

**Key:** gpus

**Expr:** max(1, ceil(peak_rps * tokens_per_q / tps_per_gpu))

**Format:** integer

**Primary:** true

**Description:** Peak token rate divided by tokens per second per GPU, rounded up. Add redundancy separately.

#### Index size

**Key:** index_gb

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

**Format:** decimal

**Description:** About 2 chunks per page and about 6 KB per chunk for vector plus metadata. Result in GB.

#### Hours saved per month

**Key:** hours_saved

**Expr:** q_day * 22 * min_saved / 60

**Format:** number

**Description:** 22 working days per month.

#### Monthly value

**Key:** monthly_value

**Expr:** hours_saved * hourly_cost

**Format:** currency

**Primary:** true

#### Monthly GPU cost

**Key:** monthly_cost

**Expr:** gpus * gpu_cost

**Format:** currency

#### Simple payback

**Key:** payback

**Expr:** if(gt(monthly_value - monthly_cost, 0), setup_cost / (monthly_value - monthly_cost), 0)

**Format:** months

**Description:** Setup cost divided by monthly value minus GPU cost. Zero means no payback at these inputs.

**Chart:**

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

**Type:** line

**X:** users

**From:** 20

**To:** 1000

**Steps:** 25

**Series:**

- monthly_value
- monthly_cost

**Disclaimer:** Planning estimate only. Throughput, tokens per question and minutes saved vary widely; measure them in a pilot before committing to hardware.

## Content

**Intro:** Use this calculator to estimate how many GPUs a private Infor Factory Track assistant needs, how large the retrieval index will be and whether the time saved justifies the cost. Every assumption is an input you can change.

**Sections:**

#### How to use it

**Body:** Start with named users and the share who use the assistant daily. Estimate questions per user per day from a pilot or from similar tools; 5 to 15 is common. Set tokens per question to include retrieved context, not just the visible answer. Enter your GPU cost as a monthly figure and set tokens per second to a value you have measured, or leave the default for a first estimate. Read the GPU estimate and payback together.

**Bullets:**

- Peak load drives GPU count, not daily totals.
- Use measured throughput when you have it.
- Run a few scenarios using the chart.

#### The formulas

**Body:** Questions per day equal named users times active share times questions per user. Tokens per day equal questions times tokens per question. Peak requests per second equal questions per day divided by an 8-hour day in seconds, multiplied by a peak factor of 4. GPU count is peak token rate divided by tokens per second per GPU, rounded up. Index size multiplies documents, pages and an assumed chunk density. Monthly value is hours saved times loaded cost.

**Bullets:**

- Peak factor 4 and 22 working days are fixed assumptions.
- Concurrency assumes about 25 tokens per second per stream.
- Index size is an order-of-magnitude estimate.

#### Reading the results

**Body:** If payback is zero, the monthly GPU cost is higher than the value at your inputs; increase adoption or questions, or reduce model size and GPU count. A modest model on one GPU can serve a surprising number of users if questions are short. Long-context retrieval and big models push GPU count up quickly. Keep a safety margin of at least one spare GPU or a failover plan if the assistant becomes business critical.

**Bullets:**

- Compare against the TCO calculator for a fuller picture.
- Treat minutes saved as a hypothesis to test.
- Do not count savings that are not realised in practice.

#### Common mistakes

**Body:** People often size from average load rather than peak, forget retrieved context in token counts, or assume large time savings per question without evidence. Another mistake is ignoring the one-time work: for Infor Factory Track, the data dictionary and permission mapping take real effort and belong in setup cost. Finally, remember that a simpler existing report may already answer the question for free.

**Bullets:**

- Size for peak, not average.
- Include context tokens.
- Count setup effort honestly.
- Validate with a pilot.

**Cta:** If you want these numbers validated on your own Infor Factory Track data and hardware, Netray can run a short sizing pilot on-prem.

**Faq:**

#### What tokens per second should I use?

**Answer:** It depends on the model, quantisation, GPU and batching. Values from several hundred to a few thousand aggregate tokens per second are common. Measure with your own model and typical prompts, then update the input.

#### Why does the calculator use a peak factor of 4?

**Answer:** Usage clusters around shift start, after meetings and at period end. A factor of 4 over the daily average is a cautious planning figure. If your usage is flatter, the GPU count will be lower than the estimate.

#### Is the value figure reliable?

**Answer:** It is only as good as minutes saved per question and loaded cost. Treat it as a hypothesis and test it in a pilot by timing real tasks with and without the assistant.

#### Does it include power and rack space?

**Answer:** Only if you include them in the GPU monthly cost. Enter an amortised figure that covers hardware, power, cooling and support.

## Search terms

Infor Factory Track AI sizing, on-prem LLM GPU sizing calculator, AI assistant ROI calculator ERP, tokens per day calculator, GPU count for LLM users, Infor Factory Track AI business case

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