On-Prem CMMS AI Assistant Sizing and Value Calculator
This calculator sizes a private AI assistant over On-prem CMMS (Maintenance Connection, MP2, Fiix alternatives) and estimates the value it returns. Change the inputs to see how many GPUs you need, how large the retrieval index is and when the project pays back.
Your numbers
Share of named users who ask at least one question on a working day.
Include retrieved context in the prompt. Retrieval-heavy questions are often 1,500 to 6,000 tokens.
Busiest hour as a multiple of the average working hour. Shift starts and handovers raise it.
Aggregate generation plus prompt throughput under batching. Measure your model on your GPU; this default is a planning assumption only.
Records, work orders, procedures or files, counted as documents.
Amortised hardware, power and support per GPU, or private cloud rental.
Your results
Planning estimate only. Throughput per GPU depends on model, quantisation, context length and serving stack, so benchmark your own setup. Time saved is a user-reported assumption, not a measured result.
Monthly value and GPU cost vs named users
Sweeps Named users from 20 to 1500, holding your other inputs fixed.
Check these numbers on your data
Optional: a short sizing review using your own user counts and document volumes.
Optional. The tool and every export work without this. No spam.
How to use it
Start with named users and the share who use the assistant on a typical day. Set questions per active user from a pilot or a survey; three to six a day is a common planning range for a plant tool. Prompt plus answer tokens should include retrieved context, which dominates cost. Then set your measured throughput per GPU. The chart shows how value and GPU cost scale with the number of named users.
- Use pilot data for questions per day
- Include retrieved context in token counts
- Benchmark tokens per second on your own GPU
- Treat minutes saved as an assumption to verify
Formulas and assumptions
Questions per day = users x daily active share x questions per user. Peak questions per hour = questions per day divided by 8, times the peak multiplier. Peak concurrency uses Little's law with a 20-second request time. GPUs = ceiling of peak tokens per second divided by tokens per second per GPU, minimum one. Index chunks = documents x pages x 600 tokens x 1.15 overlap divided by 400. Hours saved = questions per day x 21 days x minutes saved divided by 60. Payback = one-time cost divided by net monthly value.
System notes for On-Prem CMMS
Metrics such as PM compliance, MTBF and MTTR are computed from clean fields in SQL, with definitions aligned to SMRP-style metric definitions and an ISO 14224 style failure taxonomy where you have one. Retrieval handles the free text: similar failures, fixes that worked and procedures. New work orders are drafted by the assistant and entered by a planner.
Common mistakes
Sizing errors are usually in tokens and in value, not in arithmetic.
- Counting only the question and answer, and forgetting retrieved context
- Using vendor peak throughput instead of measured throughput under real batching
- Assuming every named user is active every day
- Counting all minutes saved as cash savings
Frequently Asked Questions
What default throughput per GPU should I use?
The default of 1,500 tokens per second is a planning assumption for a mid-sized open-weight model with batching. Real figures vary a lot with model size, quantisation and context length, so measure your own setup with vLLM or Ollama before buying hardware.
Why is peak concurrency calculated from a 20-second request?
Little's law says concurrent requests equal arrival rate times time in system. Retrieval plus generation often takes 10 to 30 seconds for a grounded answer, so 20 seconds is a reasonable default. Change the expression if your measured time differs.
How reliable is the hours-saved figure?
It is only as good as the minutes-saved input. Measure it in a pilot by timing how long the same question takes without the assistant. Treat early numbers as a range, and do not count the saved minutes as cash unless the work is actually reduced.
Does the index size include the model?
No. Index size covers vectors, chunk text and metadata for the documents you list. Model weights are separate and range from a few GB to tens of GB depending on model size and quantisation.
If you would like these numbers checked against a pilot on your own On-Prem CMMS data, Netray can run the sizing and a read-only proof of value on your hardware.
Related Tools
On-Prem CMMS Private AI Layer Blueprint Generator
Fill in your On-Prem CMMS environment and get a shareable architecture plan for a private, read-only AI layer: components, controls, rollout and open questions.
On-Prem AIOn-Prem LLM Total Cost of Ownership Calculator
Model the full multi-year cost of running LLMs on your own hardware, including GPU capex, power, cooling, support contracts, and operations staffing.
On-Prem AIGPU Sizing Calculator for LLM Inference
Work out how many GPUs you need to serve a given open-weight model to your user base, based on memory footprint and token throughput.
On-Prem AIPrivate RAG Corpus Sizing Calculator
Estimate chunk counts, vector index storage, raw text volume, and embedding compute time before you build a private retrieval system over your document estate.
More On-Prem AI tools
See allGo Deeper
On-Prem LLM Deployment Architecture: Reference Guide
Reference architecture for on-prem LLM deployment: inference servers, GPU sizing, RAG pipelines, and security zones for regulated manufacturers.
A Data Governance Framework for Private AI
A practical data governance framework for private AI: classification, access controls, retention, and audit patterns that satisfy CMMC 2.0 and ITAR.
Keep exploring
Free tools
- SyteLine AI Assistant Sizing and Value CalculatorSize the GPUs and estimate the monthly value and payback of a private, on-prem AI assistant for SyteLine.
- SAP S/4HANA On-Prem AI Assistant Sizing and Value CalculatorEstimate peak concurrent requests, GPUs, tokens per day, index size, hours saved and payback for a private AI assistant on SAP S/4HANA.
- Custom MES on SQL Server AI Assistant Sizing and Value CalculatorEstimate GPUs, index size, hours saved and payback for a private AI assistant over Custom MES on SQL Server.
AI on your ERP
- AI for Fiix CMMS: Ask Questions Across Work Orders, Assets and Parts Using Your Own Data BoundaryConnect a private AI layer to Fiix CMMS through its API: ask questions over work orders, assets, parts and meters, and link maintenance to your ERP.
- AI for UpKeep CMMS: Turn Work Order History Into Answers Without Handing It to a Public ModelUse AI with UpKeep CMMS through its REST API: question work orders, assets, parts and PM schedules, and tie maintenance data to your ERP and manuals.
Software
- Limble CMMSLimble CMMS explained: work orders, preventive maintenance, asset and parts tracking, API and integrations, fit for plants, limits and alternatives.
- UpKeepUpKeep explained: a mobile-first cloud CMMS for work orders, preventive maintenance, assets and inventory, with API options, limits and alternatives.