Ollama

Run LLM tests locally — no API key, no cost.

Install and pull a model


pip install "assertllm[ollama]"
ollama pull llama3.2
ollama serve

Write a test


@llm_test(
    expect.is_not_empty(),
    provider="ollama",
    model="llama3.2",
)
def test_local(llm):
    output = llm("What is 2+2?")
    assert "4" in output.content

Supported Models

Any model in your local Ollama: llama3.2, mistral, codellama, phi3, gemma2, deepseek-r1


ollama list  # see available models

Custom Host


export OLLAMA_HOST=http://my-server:11434

When to Use

Ollama is ideal for local development, CI/CD without API keys, privacy-sensitive workloads, and offline testing.

Local development — no API costs, no rate limits
CI/CD — run tests without API keys
Privacy — data never leaves your machine
Offline — no internet needed