How do I secure Ollama?

Bind Ollama to localhost only: set OLLAMA_HOST=127.0.0.1 (e.g. `sudo systemctl edit ollama` → add `Environment="OLLAMA_HOST=127.0.0.1"`), then `sudo systemctl restart ollama`.

How many Ollama instances are exposed?

112,199 Ollama instances answer the internet with zero authentication (source: Shodan count · `http.html:"Ollama is running" http.status:200`, 2026-08).

← what I check

EXPOSURE Ollama
SEVERITY CRITICAL
PROBE GET :11434/api/tags

CRITICAL

Is your Ollama exposed?

Open model API: anyone can list, run, or delete your models and burn your GPU.

Scan a host you own → Fix card Census

Why it matters

Anyone on the internet can talk to your Ollama server: list your models, run inference on your GPU (you pay the power/hardware bill), and pull or delete models. Exposed Ollama instances are scanned for within hours of going online — this is one of the most commonly found exposed AI services, with well over a hundred thousand of them visible on the public internet.

How common is it?

112,199 Ollama instances answer the internet with zero authentication. src: Shodan count · `http.html:"Ollama is running" http.status:200` · 2026-08

Counts are population-level, from third-party indexes and my own honeypots. I never scan the internet and this page makes no claim about any specific host.

Fix it

The full walkthrough lives on the fix card, kept current in one place:

Full fix card: ollama-exposed →