# abas ERP and proALPHA AI Assistant Sizing and Value Calculator

> Source: https://netray.co/tools/abas-proalpha-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 abas ERP and proALPHA.

## Category

on-prem-ai

## Erp

abas ERP / proALPHA

## Audience

- CIO
- IT manager
- Finance controller
- ERP consultant

## Tool

**Kind:** calculator

**Currency:** EUR 

**Inputs:**

#### Named users

**Key:** users

**Type:** number

**Default:** 150

**Min:** 1

**Step:** 5

**Unit:** users

**Help:** Licensed or named abas ERP and proALPHA 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:** 7

**Min:** 1

**Step:** 1

**Unit:** questions

#### Average prompt plus answer size

**Key:** tokens

**Type:** number

**Default:** 2000

**Min:** 200

**Step:** 100

**Unit:** tokens

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

#### Documents to index

**Key:** docs

**Type:** number

**Default:** 60000

**Min:** 0

**Step:** 1000

**Unit:** documents

#### Average pages per document

**Key:** pages

**Type:** number

**Default:** 6

**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:** 45

**Min:** 0

**Step:** 1

**Unit:** per hour

#### GPU monthly cost

**Key:** gpucost

**Type:** number

**Default:** 2200

**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:** 75000

**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 abas ERP or proALPHA: GPU count, token load, document index size, hours saved and payback in euros. Use the chart to compare cost and value as the user base grows.

**Sections:**

#### How to use the calculator

**Body:** Enter named ERP users and the active share, the questions each asks daily and the tokens per question and answer. German text often uses more tokens than English, so consider a higher figure. Add documents to index and their average pages, minutes saved, loaded hourly cost in euros, monthly GPU cost and a one-time setup cost.

#### Formulas and assumptions

**Body:** Active users equal named users times the active share, and daily questions follow. Peak concurrency assumes 25 percent of questions in the busiest hour at 20 seconds per answer. Load is the larger of concurrency times 40 tokens per second and busy-hour tokens per second. GPUs are the larger of the model requirement and load over throughput per GPU, and the standby adds a model replica. Index size uses 2 chunks per page at about 6 KB. A month is 21 working days. Currency is euros.

#### Reading the result

**Body:** For DACH mid-size manufacturers the GPU count is typically small. The cost that matters is the reporting layer and the German-language evaluation, which belong in setup. Value rests on minutes saved, so measure it. A zero payback means monthly value does not exceed running cost with your inputs.

**Cta:** If you want these estimates tested against your own abas or proALPHA usage, Netray can help scope a pilot. The calculator needs no contact.

**Faq:**

#### Why do tokens per question matter for German?

**Answer:** German compounds and long technical terms often split into more tokens than English. If your prompts and answers are German, use a higher token figure than for English.

#### Does it include licence costs?

**Answer:** Open-weight model licences are generally free to use, but check each licence. The calculator covers GPU running cost and a one-time setup figure you enter, not ERP vendor fees.

#### Can I use it for one ERP only?

**Answer:** Yes. The inputs are generic, so enter users and documents for the one system you plan to cover first.

#### How should I treat the payback?

**Answer:** As a hypothesis to test. Run a pilot, measure real minutes saved and update the input. Payback is simple setup cost over net monthly value.

## Search terms

abas ERP and proALPHA AI cost, abas ERP and proALPHA 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