drpranayjha.com  ›  Tools  ›  LLM Platform Sizing Worksheet

Calculators & Estimators · Solution Architecture

LLM Platform Sizing Worksheet for Solution Architects

One Excel workbook to take into a customer meeting: ask the right discovery questions, size the GPUs from weights and KV cache, produce a bill of materials, compare three years of self-hosting with three years of API, and decide. Pre-filled with a worked example; overwrite the yellow cells.

Download the worksheet (.xlsx)
Excel 2010 or later, or LibreOffice. 9 tabs, 240 formulas, no macros. About 40 KB.
Currency selectable: INR, USD, EUR, GBP, SGD, AED, SAR, AUD, CAD, JPY (editable FX table).
Version 1.1 · September 2026 · free to use and adapt; keep the attribution.

The method the sheet walks, left to right:

model → precision → weight memory → KV cache (context × concurrency) → VRAM needed → GPU type and count → measured throughput → N+1 → BOM → 3-year TCO vs API → decision

What is inside

TabWhat you do there
READMEHow to run the meeting with it, colour legend (blue on yellow = you type; black = formula; green = pulled from another tab), and what the sheet deliberately does not do.
SettingsPick the working currency from a drop-down. Indicative prices are stored in INR and converted through an editable FX table; every price line also has a "Your quote" cell in the chosen currency that overrides the converted figure. Headers, totals, the TCO and the proposal sentence all follow the chosen currency.
1 Discovery22 questions to ask the customer. Each has why it matters, an answer cell, a notes column for the customer's own words, and the sizing step it drives. Numeric answers flow straight into sizing. Model and precision are drop-downs.
2 SizingTokens per day → weights with runtime overhead → KV cache per token (looked up from the model's layers, KV heads and head dimension) → KV cache at peak concurrency → VRAM needed → cards, rounded to tensor-parallel sizes → how many concurrent conversations the design actually holds → a plain verdict. Then the throughput check against a measured tokens-per-second figure you enter, GPUs and servers to quote with an N+1 toggle, and storage, RAM, NVMe, power and rack units. At the bottom, a comparison table runs the same workload against every card in the library.
3 BOMQuantities pulled from sizing, indicative Indian list prices to replace with quotes, one-time total, and recurring options (NVIDIA AI Enterprise, commercial Kubernetes, support) with include toggles.
4 TCOSelf-hosted versus API over the horizon you choose: hardware, power, recurring, people, token cost. The cost ratio, the break-even in tokens per day, and a formula-written sentence for the proposal.
5 DecisionThe five self-host questions with a counted verdict, and a twelve-item checklist to complete before any purchase order.
Model libraryArchitecture facts for 11 open models (parameters, layers, KV heads, head dim → KV KB per token). Add rows; verify against the model card.
GPU library10 cards with VRAM, TDP and indicative price. Add rows for whatever you are quoting.
Two things the sheet will not do for you. It does not measure throughput: tokens per second depend on model, precision, batch size and engine, and change every quarter. Rent the exact card for an hour, run vllm bench serve with the customer's token profile, and type the result in. And it does not price licences: every yellow price is an order-of-magnitude list figure to be replaced by a quote.

Where it comes from

The worksheet is the calculation half of the post I run a 70B model for free and own no GPU. So where does the enterprise AI stack come in?, which walks one AI application end to end and explains every term with a plain example or a VMware equivalent. Question 8 of that post is this sheet, in prose.

For the product-level design (which Kubernetes, which storage, which vector database, which observability) use the Enterprise AI Stack Builder; it draws the layers and produces the "what". This worksheet produces the "how many". Together they are a solution document.

Worked example baked in