Ollama Commands

🧠 Basic Ollama Commands

▶️ Run a model

ollama run llama3

Runs the model interactively (downloads it first if needed).

📥 Pull (download) a model

ollama pull mistral

Downloads a model without running it.

📤 Push a model (to registry)

ollama push yourname/model

📃 List installed models

ollama list

❌ Remove a model

ollama rm llama3

💬 Running Prompts (Non-interactive)

One-shot prompt

ollama run llama3 "Explain quantum computing simply"

Using stdin

echo "Write a poem about space" | ollama run llama3

🔌 Server & API

Start Ollama server

ollama serve

Default runs at:

<http://localhost:11434>

🔍 Model Info

Show model details

ollama show llama3

🧪 Advanced / Useful Flags

Run with system prompt

ollama run llama3 --system "You are a strict teacher"

Set temperature

ollama run llama3 --temperature 0.2

Keep model loaded

ollama run llama3 --keepalive 5m

🧰 Popular Models You Can Use

• llama3 (by Meta)

• mistral (by Mistral AI)

• gpt-oss (by OpenAi)

• phi3 (by Microsoft)

• gemma (by Google)