How to list Ollama models

The model list shows which models are installed in the local Ollama model store. It is the first check before running, copying, removing, or calling a model from the API.

The CLI and API expose the same inventory through different formats. Use ollama list for terminal work and api/tags for scripts that already communicate over HTTP.

An empty list means the server is reachable but has no local models. A missing model error after a non-empty list usually means the script used the wrong tag or connected to a different server.

1. List local models with the CLI.

   $ ollama list
   NAME           ID              SIZE     MODIFIED
   gpt-oss:20b    17052f91a42e    13 GB    6 months ago

2. Check the same inventory through the API.

   $ curl -s http://localhost:11434/api/tags
   {"models":[{"name":"gpt-oss:20b","model":"gpt-oss:20b"}]}

3. Use the exact name and tag in later commands.

   $ ollama run gpt-oss:20b "Return only OK."
   OK

4. Inspect details when several similar tags exist.

   $ ollama show gpt-oss:20b
     Model
       parameters          20.9B
   ##### snipped #####

5. Pull the model if the list does not contain the required name.

   $ ollama pull gpt-oss:20b
   success

   Related: How to pull an Ollama model