“As someone with an old PC, I want to know what it can run before I buy anything, so that I don't spend on hardware I don't need.”
Start with the assessment, then check which system fits the machine.
I set up local AI assistants on hardware people already own, then leave a setup they can maintain. Below: a few things I have built, the areas I work in, and notes from the job.
$ free -h total used free Mem: 31Gi 9.2Gi 18Gi $ nvidia-smi --query-gpu=name,memory.total --format=csv name, memory.total [MiB] NVIDIA GeForce RTX 3060, 12288 MiB $ df -h /srv /dev/nvme0n1p2 1.8T 612G 1.1T 36% /srv # 32 GB RAM + 12 GB VRAM: the comfortable range for 14B Q4
Read the story closest to yours; the practical next step follows it.
“As someone with an old PC, I want to know what it can run before I buy anything, so that I don't spend on hardware I don't need.”
Start with the assessment, then check which system fits the machine.
“As a self-hoster, I want one entrance for my services and certificates that renew themselves, so that adding a service does not break the rest.”
Look at Traefik, and at the security baseline before exposing anything.
“As a GPU owner, I want dsh to survive reboots and upgrades, so that I can use the assistant instead of babysitting it.”
Harness first, then a VRAM and context check.
“As a small team, I want shared local AI with monitoring, so that we notice problems before our users do.”
k3s for several nodes, Grafana for the alerts.
Client names and machine details are left out. What changed is not.
One person's dsh setup, moved into a container so it starts on boot and an upgrade can be undone.
Certificates renew themselves, and a single hostname can move without taking the rest offline.
A small registry with permissions and cleanup, instead of copying images between laptops.
Fill in what you have. The result is a rough starting point for a conversation, not a benchmark; everything runs in your browser and is never uploaded.
Fill in the fields and press "Generate assessment". The result is calculated locally; nothing is uploaded. It will list: RAM, disk, GPU/VRAM, upstream bandwidth, a rough model tier, and what to check next.
The assessment stays in this tab. Email is only sent when you choose to send it.
Six areas. Scope gets agreed before any work, then a price. A Proxmox box running one container and a three-node cluster with monitoring are not the same job.
With a few services, ports and certificates end up everywhere. One entry point, routing by hostname, certificates renewed automatically.
See the scope →Images live on one machine, so the next one has to rebuild. A private registry means every machine pulls the same version.
See the scope →Reach home services without opening an inbound port, with Access policies and origin checks.
See the scope →dsh and its dependencies in a container: no reconfiguring after a reboot, and upgrades you can roll back.
See the scope →From one Docker host to several nodes: Ingress, storage and monitoring. First decide whether you need it.
See the scope →A full disk, an expiring certificate, a restart loop. At least let your phone ring.
See the scope →Not a course, not an open-ended engagement. One review, one written plan, and a list of what to change first.
A remote look at your hardware, system and services, with a written plan you can act on: what can run, what is stuck, what to change first.
No online checkout yet. Read the scope, then send your setup by email.
Written while debugging or deploying. They show how I think about a problem; they are not the product, and they are not the pitch.
The assessment is free and runs in your browser. Everything after it gets scoped in writing first.
Put CPU, RAM, disk, GPU and bandwidth into the assessment and get a text you can paste.
Read the Cloudflare, security and systems guides to see whether the limit is hardware, network or the OS.
Email the assessment and your goal. If it fits, you get a quote; if not, you hear that too.
Configuration, documentation and verification steps, so the next change is yours.
Most problems are not a missing advanced trick. They are basic concepts that never lined up.
Know what the hardware can do before deciding what to buy.
Free guides make no promises about results; paid work does not take over accounts or run 24/7.
Every page has a Markdown version and structured metadata, so your own assistant can cite it.
Saying what is out of scope is more useful than saying how good we are.
No shop links, no affiliate commission.
The same model behaves differently with another driver, quantization or context length. You get a tier and a way to verify it.
Work happens on your machine. Passwords and tokens stay with you.
I run a home server, containers and local models. The notes and cases come from actual debugging, not a content team, and I take a small number of deployments so the site stays honest.
More about me →The concepts and the order of decisions are readable. When you actually try it, use a machine you can break, not your main one.
Not to benchmark level. It uses VRAM, RAM, disk and bandwidth to place you in a rough tier, enough to decide whether to try and what to check first.
A course cannot cover every home setup. The method is free; work in your specific environment is a project.
No. What can be verified in your environment gets verified; third-party, driver and model limits are not covered.
Yes, use the language switch in the header.
No. The assessment runs in your browser: no upload, no cookie, no analytics. Nothing leaves it unless you send an email.
The usual limit is not a slow CPU. It is VRAM, RAM, disk or network running out first. Writing the configuration down as a fixed text makes both your own research and an email exchange easier.
The assessment gives an order of magnitude: not tokens per second, but roughly which tier you are in, whether RAM or disk is clearly short, and whether multi-GPU or bandwidth is worth spending on.
The three guides are maintained by topic, without an “always current” label. Found an error? Email; once it is confirmed, the page is fixed. Paid projects are quoted per project, with scope in the quote.
[email protected].Accept: text/markdown to a page URL to get the Markdown mirror.
Run the assessment first, or send your setup and goal by email. The reply says whether it fits and what happens next.