Self-Hosted Odoo AI Assistant Sizing and Value Calculator
This free calculator estimates GPU count, token load, attachment index size, hours saved and payback for a private AI assistant on self-hosted Odoo. Use the chart to see how cost and value change with user count.
Your numbers
Licensed or named Self-Hosted Odoo users who could use the assistant.
Percent of named users who ask at least one question per day.
Include retrieved context. Typical range 1000 to 3000.
Measure in a pilot; this is the most uncertain input.
Amortised purchase plus power, space and support, or a private cloud rate.
Assumption: depends on model, quantisation and batching. Measure on your hardware.
Integration, indexing, testing and rollout effort.
Your results
Planning estimate. Throughput, minutes saved and token counts vary widely; measure them in a pilot before committing budget.
Monthly value vs GPU cost by named users
Sweeps Named users from 10 to 1000, holding your other inputs fixed.
Optional Odoo pilot scoping
We can help turn these estimates into a measured pilot on your Odoo data.
Optional. The tool and every export work without this. No spam.
How to use the calculator
Enter Odoo named users and the share that use the assistant each day, plus questions per active user and tokens per question and answer. Add the attachments you plan to index and their average pages, then minutes saved, loaded hourly cost, the monthly GPU cost and a one-time setup cost. Outputs show peak concurrency, GPUs with a standby, index size, hours saved and payback.
Formulas and assumptions
Active users are named users times the active share. Daily questions multiply by questions per user. The busiest hour is assumed to carry 25 percent of daily questions 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 one model replica. Index size is 2 chunks per page at about 6 KB. A month is 21 working days. API call load on Odoo is not included.
Reading the result
Odoo sites are often small enough that one GPU covers load, so cost is dominated by setup and attachment indexing. The value depends on minutes saved per answer, which you should measure on real tasks. If payback is zero, value is below running cost for these inputs. Try fewer GPUs, a smaller model or a narrower scope.
Frequently Asked Questions
Does the Odoo server need extra capacity?
Assistant calls become extra API requests. For modest use this is small, but heavy search_read calls on large tables can matter, so limit fields and rows and consider a replica for aggregates.
How many attachments should I index?
Start with documents users actually search, such as vendor quotes, certificates and work instructions. Index size is small compared with model memory, but ingestion time grows with volume.
What throughput per GPU is realistic?
Aggregate throughput depends on model size, quantisation and batching. A range of 800 to 2500 tokens per second is common for mid-size models; measure on your hardware.
Can I compare scenarios?
Yes. Change users, questions per day or minutes saved and watch the outputs and chart update. Export the result to share with finance.
If you want these estimates checked against your Odoo usage, Netray can help scope a pilot. The calculator is free and needs no contact.
Related Tools
Self-Hosted Odoo Private AI Layer Blueprint Generator
Generate a shareable architecture plan for adding a private, on-prem AI assistant to Self-Hosted Odoo, with components, security controls and a three-phase rollout.
On-Prem AIOn-Prem GPU Sizing Calculator for ERP AI
Work out how much GPU memory and how many cards you need to serve an open-weight model to your ERP users on-prem.
On-Prem AIOn-Prem AI ROI Calculator
Turn hours saved per employee into annual net benefit, payback months, and 3-year ROI for an on-prem AI investment.
On-Prem AIVector Database Sizing Calculator
Convert vector count, embedding dimensions, and precision into a real storage footprint, including index overhead and replica factor, before you pick a vector database.
More On-Prem AI tools
See all- On-Prem LLM Total Cost of Ownership Calculator
- GPU Sizing Calculator for LLM Inference
- On-Prem vs Cloud AI Cost Comparison Calculator
- Self-Hosted LLM Hardware Estimator
- Air-Gapped AI Readiness Assessment
- LLM API vs Self-Hosted Cost Calculator
- RAG Infrastructure Sizing Calculator
- Open-Weight Model Selector
- On-Prem AI Deployment Checklist
Keep exploring
Free tools
- Self-Hosted Odoo Private AI Layer Blueprint GeneratorGenerate a shareable architecture plan for adding a private, on-prem AI assistant to Self-Hosted Odoo, with components, security controls and a three-phase rollout.
- Odoo Manufacturing Setup ChecklistA practical checklist for configuring Odoo Manufacturing from inventory foundations through BOMs, work centers, planning and go-live.
- Macola AI Assistant Sizing and Value CalculatorEstimate GPU count, token volume, index size, hours saved and payback for a private on-prem AI assistant on Macola.
ERP fixes and how-tos
- Self-Hosted Odoo AI Assistant: Private Architecture With a Local ModelAdd a private AI assistant to self-hosted Odoo: external API with user API keys, record rules respected, PostgreSQL replica, local model and audit trail.
- Odoo Manufacturing Reports: Production Analysis, Cost and ForecastBuilt-in Odoo manufacturing and production reports, how to forecast demand and component needs, and how to build custom MRP reports with SQL or Studio.
- Odoo Manufacturing Tutorial: From BOM to Finished ProductOdoo manufacturing tutorial for small manufacturers: set up products, BOMs, work centers and operations, run a manufacturing order, and what to check in Odoo 19.
AI on your ERP
- AI for Odoo Manufacturing That Reads Your Own Database, Not a Vendor's CloudAdd grounded, natural-language AI to Odoo Manufacturing without sending MRP, BoM, or work order data to a public model. On-prem or private cloud, ORM-native.
- AI for Odoo Manufacturing (MRP): BOMs, Work Orders and ShortagesAI for Odoo Manufacturing: BOM checks, work order delays, reordering rules and plain-language questions over mrp.production data, on-prem or private cloud.
Integrations
- How to add AI agents to OdooHow to add AI agents to Odoo Manufacturing: a tool layer over the external API, approval before writes, and agents for MRP exceptions, POs and quality.
- How to use Claude with OdooHow to use Claude with Odoo: MCP connectors, the Anthropic API, AWS Bedrock or Google Vertex hosting, data handling, and an on-prem alternative.
Software
- OdooWhat Odoo is, how its open-source Community and Enterprise editions differ, how the manufacturing apps and XML-RPC API work, and which alternatives to compare.
- SAP Business OneSAP Business One explained for small manufacturers: modules, Service Layer and DI API, deployment, limits, alternatives and where AI helps on top of it.