Setting up a private AI on your computer
What installation actually looks like · about a 5-minute read
The short version: with most private-AI tools, "setup" means opening a terminal and choosing model files. With Garnet you open it once and it sets itself up for your machine, choosing and configuring everything on its own. This page walks through exactly what that looks like, and how to prove the privacy for yourself once it's running.
1. Check your computer can run it
A private AI runs the model in your computer's memory (RAM), so the only real requirement is having enough room. The guide-rails:
- 8 GB of memory — runs a genuinely useful everyday model. This is where most laptops land.
- 16 GB — a noticeably smarter model; the sweet spot for most people.
- 32 GB and up — room for larger, sharper models.
It runs on Mac or Windows, and Apple-Silicon Macs (the M-series) punch above their memory because they share it cleverly with the chip. Tell us roughly how new the machine is and how much memory it has, and we will say plainly where you land.
2. How you would get it
When there is a build to hand out, it will be announced here first, and telling us you want one is the way to hear about it — one email, the day it lands, and that is the whole of it. Your address, and your address alone.
Why commission rather than ship? Because the thing we would ship is a machine rather than an installer, and we would rather say so than put a button here that sends you an apology later.
3. Install it in one step
This is the part that's different. With the do-it-yourself tools, installing is where you meet the command line, the model catalogue, and the settings. With Garnet, you open the app and it sets itself up:
- It opens like any app. Click it, and it starts.
- It picks the model. Garnet looks at what your computer can carry and fits a model to it, so you get the sharpest version your hardware allows, and you can leave the details to it.
- It configures itself. It is ready the moment it finishes setting up.
The first setup downloads the model — a single large file — so it takes a few minutes on a normal connection. After that, it's all on your computer and starts instantly, online or off.
4. Start using it
You talk to it like any assistant — a plain chat window. A good first thing to try is something real that has to stay off a cloud chat box: a sensitive email to rewrite, a confusing letter to explain, a decision to think through out loud. If you want a running start, the starter guide has ten prompts to copy straight in.
5. Prove the privacy yourself
Test it rather than take our word for it — pull the cable. Once Garnet is running, unplug your internet (or turn off Wi-Fi) and ask it something. It keeps right on answering. That's the whole argument in one move: if it still works with the cable out, everything you typed stayed on the machine. Your chats live there and there alone, which is the whole of what anyone could reach. If you want the precise version of what "private" means here, here's exactly what we can see and what stays yours.
Before the optional upsell, the honest part: everything above describes the build you commission, and the section below is the half that is available today. The next section is for people who would genuinely rather hand the whole thing to someone, and you are free to skip it.
Or have us set it up for you
If "open the app and it sets itself up" is still more than you want to deal with — or you want it tuned around your specific work — we'll do it on your computer, with you, in a guided session. The same conversation also scopes the bigger end: a model larger than a laptop can hold, or a dedicated, always-on system on its own hardware, built by the engineer who stands behind it.
Book a setup session A scoping call is free, with your card left in your pocket. You pay only if you decide to go ahead.
If the fit is wrong
A few honest edge cases:
- An older or smaller computer still runs Garnet — just with a smaller model, so expect quick-and-useful rather than its sharpest. The checker will tell you plainly if that's you.
- Want a model bigger than your machine can hold? That is a hardware question rather than a setup one, and it is exactly what a dedicated build is for.
- Comparing it to the developer tools first? Here's an honest look at Garnet vs Ollama, LM Studio, Jan and LocalAI so you can pick the right one.
More: the plain-English starter guide · what we can see and what stays yours · back to top.
