Home / Local AI Decision Kit
New · Should you run your own AI?

Local AI Decision Kit

Open-weight models on your GPUs vs. paying per token. Break-even volume and month, a blind quality bake-off protocol, and the 30-point ops audit that kills GPU impulse buys.

XLSX + DOCX · instant download
Local AI Decision Kit cover
What's inside

The decision calculator (XLSX, 271 live formulas)

Break-even volume and break-even month for self-hosting vs. API pricing — including the MLOps staffing line most comparisons quietly omit, plus the capacity ceiling: the month your workload outgrows the hardware.

The decision framework (DOCX)

Three go/no-go gates, a blind quality bake-off protocol with pass/fail thresholds, and a 30-point operations audit built to kill GPU impulse buys before they hit the budget.

Who it's for

Teams deciding whether to run open-weight models on their own GPUs instead of paying per token — and the skeptics who have to sign off on the purchase.

How it works
  1. Enter your current token volumes and API rates.
  2. Add the GPU/server quote you're considering and honest staffing assumptions.
  3. Run the bake-off protocol before you commit — quality gates first, economics second.
Questions

Do I need special software?

Excel or LibreOffice for the calculator (verified), any word processor for the framework document.

Does it assume a specific model or vendor?

No — it's vendor-neutral. You supply the quotes and volumes; the math doesn't care whose logo is on the hardware.

What if my volume is small?

Then the calculator will tell you that, plainly. "Keep paying per token" is a valid verdict — the kit exists to find the truth, not to sell you on GPUs.

Also in the catalog
Get Local AI Decision Kit — $89