Ollama

Run Commands

Start interactive chat sessions with LLMs using Ollama. Run models with custom parameters, set system prompts, and control generation settings.

7 commands

Pro Tips

Press Ctrl+D to exit chat, or type '/bye' to end the session gracefully.

Use '/set system <prompt>' in chat to change the system prompt mid-conversation.

Pass '--verbose' to see generation speed and token statistics.

Common Mistakes

First run loads the model into memory - subsequent prompts are much faster.

Running multiple models simultaneously multiplies memory requirements.

Commands

Start chat session

$ ollama run llama2

Start interactive chat with a model.

One-shot prompt

$ ollama run llama2 "Explain quantum computing in simple terms"

Run a single prompt and exit.

Pipe input

$ cat document.txt | ollama run llama2 "Summarize this text"

Process file content through the model.

Run with verbose output

$ ollama run llama2 --verbose

Show generation statistics and timing.

Run code model

$ ollama run codellama "Write a Python function to sort a list"

Use code-specialized model for programming tasks.

Run with system prompt

$ ollama run llama2 --system "You are a helpful coding assistant"

Set a persistent system prompt for the session.

Run vision model

$ ollama run llava "Describe this image" ./photo.jpg

Analyze images with multimodal models.