
Cloud AI is fast and convenient. A box in your office costs money up front and keeps your files in the building. Drop in a financial file and watch the trade: the same analysis written at the speed of a frontier cloud model and four local machines, from $500 to $5,000.
A bank export, a ledger, a sales report. Anything with amounts in a column.
● Read inside this browser tab. Nothing is uploaded, to us or anyone.
Tap any lane to watch that machine write its answer below.
Simulated playback. The page does not run an AI model. It works the numbers out from your file, writes one summary, and replays that summary at each machine's published writing speed. The two accuracy figures on each lane are published test scores for that model, explained below. A token is about three quarters of a word.
Every lane wrote the same words. The only thing that changed was how long you waited. For a summary like this one, the gap between the cloud and a well-chosen box is a few seconds. On the smallest box you wait about seven times as long.
Speed comes from the hardware and the size of the model. A bigger model on the same box writes slower. That trade is the first thing we size.
The totals in the demo were added up by code, so they match in every lane. The two percentages on each lane are something else: how that model scores on two published tests, one easy to relate to and one hard on purpose. The next section explains both.
Accuracy depends on the job. So each lane carries two published scores for its model: one for reading financial statements, and one for hard math with nothing checking the work. Neither is a score for your files or for the demo above.
A test from researchers at ETH Zürich asks 250 questions about 10-Q-style financial tables: look up a figure, add a few lines, find the highest quarter, work out gross profit. The correct answer is calculated from the table itself, so the answer key involves no judgment call.
V-FiLLM, 10-Q setting, questions asked in one go. Six models were tested. No frontier cloud model was among them, and neither was a 20B or a 4B model, so those lanes read "not tested". The paper describes its 10-Q tables as real filings in one place and as synthetic statements modeled on a 10-Q in another. Bars start at zero.
One caution from the same paper. On a harder question set, the 9B model fell to 55.2% when asked everything at once. Broken into steps, it came back to 86.8%. On a small box, how you ask matters.
The second test is hard on purpose. FinanceReasoning's hard set is 238 calculations of about eight steps each, like a multi-step mortgage problem, and an answer counts only if it lands within 0.2% of the correct figure. The best cloud models set the bar at 91.60%. Everything else is distance to that line.
Scores as published by AIMultiple, updated 17 Nov 2026. Each model reasoned step by step on its own; the source does not say whether tools were allowed. Models small enough for the $1,000 and $500 boxes were not in that test. Bars start at zero.
The $5,000 box's model scores 81.09% today. In the test's original 2025 paper, the best cloud model scored 81.1% reasoning step by step. Roughly, a box in your office is where the frontier was when this test came out. Those are two separate test runs, so read it as a rough marker.
At 81%, about one hard calculation in five comes back wrong when nothing checks it. At 68%, about one in three. That is too many to trust unaided.
The test's authors found that models did better when they wrote a short program to do the arithmetic. One went from 65.6% to 83.6% that way. A good setup has the model explain and software calculate.
A published score is a starting point. Before anyone buys a box, we run candidate models against your own documents and questions, and count what they get right.
Hardware budget only, with one example machine each. Prices move monthly, so read these as an order of magnitude.
Setup, model selection and training are quoted separately. Example hardware, speeds and accuracy scores per the sources below. Speeds are for one person asking at a time with a short prompt, and fall as documents get longer.
A first conversation covers what you want the model to do, which files it would need, and whether a local box, a business-tier cloud contract, or both is the right fit. If it is a box, we run your actual documents on candidate hardware before you buy anything, then handle procurement, the model and the training.
Start a conversation →doug@studio111labs.com