Ollama

Models Commands

Download, list, and manage local LLM models with Ollama. Pull models from the registry, view installed models, and remove unused ones to manage disk space.

7 commands

Pro Tips

Use 'ollama pull model:tag' to download specific model versions (e.g., llama2:13b).

Run 'ollama list' regularly to check disk usage - models can be several GB each.

Use quantized versions (q4_0, q5_1) for faster inference and lower memory usage.

Common Mistakes

Large models (70B+) require significant RAM (32GB+) and may not run on consumer hardware.

Pulling models downloads gigabytes of data - ensure sufficient disk space and bandwidth.

Commands

Pull a model

$ ollama pull llama2

Download a model from the Ollama library.

Pull specific version

$ ollama pull llama2:13b

Download a specific model variant or size.

List installed models

$ ollama list

Show all locally available models with sizes.

Remove a model

$ ollama rm llama2:7b

Delete a model from local storage.

Show model info

$ ollama show llama2

Display model details including parameters and license.

Copy model

$ ollama cp llama2 my-llama2

Create a copy of a model with a new name.

List running models

$ ollama ps

Show models currently loaded in memory.