LZLZL/AI toolchain/Cloud · Mechanics
FREEMedium · Practice D · Cloudsizing

Buying a box:
sizing and region

2026-08-21 · Criteria only, no head-to-head

You passed at least one of the previous page's three tests, so it is time for a machine. Here is how to size it — with no provider comparison, for the reason in §5.

In this pagethree selection criteria, what to prepare first. No provider rankings, and nothing about which one I use or where.

1RAM: size for peaks, not steady state

The easiest thing to get wrong. Steady usage looks like a few hundred megabytes, so you buy the smallest tier — and then get killed by the memory limit during one compile, one dependency install, one large file.

Memory spikesWhy they get forgotten
Installing dependencies / compilingOnly happens at deploy — but when it happens it is the peak
Agent handling long contextA large file costs memory, not only tokens
Two jobs at onceOverlapping schedules (page 11, trap one) double it outright
System updatesRare, but competes with your service when it happens
Being killed for memory is brutal to diagnose

There is no error. The process is simply gone. The logs usually say nothing — because whatever was writing them died too. You see "the service vanished for no reason" and spend a long time hunting for a bug that is not in your code.

So: go one tier up. On memory, the money saved never covers the debugging time.

2Region: latency and availability, not distance

ConsiderationHow to think
Latency to the model endpointThe important one — every agent turn is a round trip; latency times turns is your waiting
Latency to services it usesIf it mostly talks to one API, sit near that API
Latency to youAlmost irrelevant — you only SSH in occasionally
Availability and complianceSome services are not offered in some regions. Check first, or the box is useless

The classic mistake is "pick the one nearest me". But between you and that box there is a trickle of SSH, while between it and the model endpoint there is traffic on every single turn. Wrong thing optimised.

3Disk: leave room for logs

Leave room forNote
LogsConfigure rotation or they fill the disk eventually. Day-one job
Container imagesWith Docker, old images pile up
Sessions and memoryAn always-on agent's history only grows
A full disk is the ugliest class of failure

Because everything breaks at once: services cannot log, databases cannot write, and you may not be able to run commands after SSHing in. And the cause has nothing to do with whatever you were actually doing.

Prevention is cheap (set up log rotation). Recovery is not. Do it on day one.

4Three things to have ready first

PrepareWhy in advance
An SSH key pairChoose key login at creation — far easier than retrofitting
Clarity on what it will runDetermines sizing, and also page 22's question: should it touch secrets at all
A rebuild noteEven a few lines. You will rebuild eventually, and you will be grateful
If you are about to open one

This step means signing up with a provider. This site does not run provider comparisons — I use one of them myself, and no ranking produced from that position comes out clean. Hence criteria above rather than a shortlist.

Saying it in full: if you are going to open one, you can go through my referral link: 👉 sign up for Vultr. I have not checked the terms of that referral programme — how much it pays, whether the referred side gets anything, whether there are thresholds — so this page promises nothing about it; read their own page. Going through it is a small encouragement for these pages, and keeps me writing the rest of them. Not using it is entirely fine — any other provider works just as well. Every step from the first hour to running it as a service is identical on any VPS; nothing in this thread depends on a particular vendor's features.

Practical notePut your SSH public key in at creation rather than opening with a password and fixing it later — a public box is being scanned from minute one, so keep the password window as short as possible.

5Why no comparison

This site has a fixed rule: claim no neutrality and you owe no disclosure; the moment a page is about the economics of a business you are in, you must disclose.

A head-to-head is the archetypal neutrality claim. Since I use one of these providers, no ranking lands clean — so there is no ranking. You get the criteria and do your own. Same rule as the relay page.

Nature of this page The three criteria are this site's practice, not any vendor's recommended configuration. This page contains no provider comparison or ranking.
Disclosure This page contains my own referral link (Vultr), in the box at the end of §4. The terms of that referral programme are unchecked by me, so no statement is made about rebates or discounts.
Not given here Specific plans or prices. Specs and pricing change faster than this page; use the official pages.
Not in this page How many machines I run, in which regions, at what size, doing what.

RelatedRead next

D · Cloud
The first hour: the order does not reverse
D · Cloud
When a VPS is actually required
D · Cloud
Run it as a service, so it restarts itself
D · Cloud
Key isolation, monitoring, backups, switching off
An educational and engineering record — not a review or endorsement of any third-party product. Commands, config keys, prices and terms are per each vendor's official docs; this page states when it was checked and all of them can change without notice — verify before you copy anything. Self-hosting is your own responsibility: keys, accounts and data are on you.