QuietWatts
Real hardware. Real benchmarks. No cloud required. Method v1.0 Runs 1 Machines 2

Writing

Everything I publish, newest first. Use the filters to narrow by article type or topic.

Type
Topic

13 articles

How-to Local AI

How I Benchmark a Local LLM

The protocol, the commands, and the first QuietWatts row: Qwen3.8 27B on a DGX Spark, measured by a harness rather than a stopwatch on a chat window.

Explainer NAS & Storage

Can You Run AI on a NAS?

Usually yes, and it will be slower than you want. But the electricity is already paid for, which changes the argument more than the speed does.

Explainer Local AI

Which Local Model Should You Run?

Your hardware sets a ceiling and the arithmetic can tell you exactly where it is. Which model to pick under that ceiling is a judgment nobody can make from a table, including me.

How-to Local AI

Run Your First Local LLM with Ollama, Step by Step

Install Ollama, pull a model that fits your hardware, and chat with a local LLM in about fifteen minutes, then the handful of commands that make it usable afterwards.

Explainer Local AI

What a 32k Context Window Costs You in Memory

Context is not free and it is not fixed. The cache grows with every token you exchange, which is why a model that loaded fine runs out of memory an hour into a conversation.

Explainer Lab Infrastructure

How Loud Is Two Machines in One Room?

Adding a second machine adds three decibels, not double the noise, and that one fact changes where the money should go when a lab gets too loud.

Explainer NAS & Storage

NAS RAID Levels Explained for Newcomers

What each RAID level costs you in capacity, what it actually protects against, and why the rebuild after a failure is the part worth planning for.

Comparison Self-Hosted Software

Proxmox vs. TrueNAS vs. Unraid

Three systems built around three different assumptions about what a home server is for. Picking well means knowing which assumption matches yours, not which is best.

Explainer Local AI

Quantization Explained (GGUF, AWQ, and Friends)

What quantization does to a model, why a four-bit file is never four bits, and the thing it buys you that almost nobody mentions.

How-to Lab Infrastructure

What Size UPS Does a Home Lab Need?

Size on volt-amps, not on minutes, because the runtime you need arrives free and the rating on the box is not watts.

Comparison Home Server Compute

Cloud GPU vs. Owning Hardware: The Real Cost Math

What owning the hardware actually costs against paying per token, worked out at three usage levels, including the cases where buying never pays back.

Explainer Lab Infrastructure

What a Homelab Really Costs in Electricity

The arithmetic behind a homelab power bill, worked out from one number you can hold in your head, plus where the watts actually hide and which levers move the total.

Explainer Local AI

How Much VRAM You Need for Every Model Size

The memory arithmetic for running a local model, worked out for every common size and quantisation level, including the term most guides leave out.