Deployed llama3.2:1b locally via Ollama

I wanted to start this series with the most boring possible first step — not because it's impressive, but because everyone skips it. Every tutorial about running LLMs locally jumps straight to "here's how you fine-tune it" without ever answering the question I actually had: what does this thing cost me in memory, for real, on my machine?

So: installed Ollama, pulled llama3.2:1b (Meta's smallest Llama 3.2 model — 1 billion parameters, small enough that it downloads in a couple of minutes instead of eating your afternoon), and loaded it with a throwaway prompt just to force it into memory.

Here's the thing nobody tells you up front: the download size and the loaded memory size are not the same number. The model file on disk is about 1.3GB. Once it's actually loaded and running, ollama ps showed it sitting at 1.5GB, and digging into the actual process with ps aux put the real RSS at 1.24GB.

$ ollama ps
NAME           ID              SIZE      PROCESSOR    CONTEXT    UNTIL
llama3.2:1b    baf6a787fdff    1.5 GB    100% GPU     4096       About a minute from now

$ ps aux | grep ollama
flyers  95443  0.1  7.7  436962064  1295248  ??  S  llama-server --model ... -c 4096
flyers   1456  0.0  0.1  436899728    22336  ??  S  ollama serve

Not a huge gap, honestly — the loaded footprint is only modestly bigger than the file itself. But "modestly bigger" is still a real number, and it's the one that actually matters if you're ever going to run this thing in a container with a memory limit on it. The download size is marketing. The RSS number is what you'd actually put in a Kubernetes resource request.

Correction (Aug 19, 2026): this model is Q8_0 quantization, not an unspecified default — see Entry 04 for the full breakdown across quantization levels.