Ollama

Ollama is an efficient tool for managing and running local large language models (LLMs). It greatly simplifies AI model deployment. With minimal environment setup, you can pull, run, and manage models on your local device.

Install Ollama

curl -fsSL https://ollama.com/install.sh | sh

For building from source locally, refer to the official documentation.

Usage

Pull a model

This command downloads the model files from the Internet.

ollama pull deepseek-r1:1.5b

Run a model

This command starts the model. If it is not cached locally, Ollama will download it automatically and then run it.

ollama run deepseek-r1:1.5b

Show model information

ollama show deepseek-r1:1.5b

List downloaded models

ollama list

List loaded models

ollama ps

Stop a running model

ollama stop deepseek-r1:1.5b

Remove a model

ollama rm deepseek-r1:1.5b

References

For more details about Ollama, refer to the official documentation.

Install Ollama​

Usage​

Pull a model​

Run a model​

Show model information​

List downloaded models​

List loaded models​

Stop a running model​

Remove a model​

References​