Official documentation
Ollama integration
Home Assistant project, Home Assistant, 2026
Read the originalRead on October 17, 2026
- What it is
- The Home Assistant documentation for the Ollama integration, which connects a local language model server to Assist, including its context window default, its entity advice and its requirement for tool support.
- How much weight it carries
- Official integration documentation. Model behaviour changes with each model, so the advice on entity counts is the project's general guidance and not a test of any one model.
Facts taken from this source
- Home Assistant's default context window for the Ollama integration is 8k tokens, which is larger than the default of 2k on the Ollama server.
“Home Assistant defaults to 8k, which is larger than the default value in Ollama Server (2k)” (Context window size)
- Home Assistant recommends exposing fewer than 25 entities to a local language model when you experiment with Ollama, and warns that smaller models make more mistakes.
“If you want to experiment with local LLMs using Home Assistant, we recommend exposing fewer than 25 entities.” (Controlling Home Assistant)
- Home Assistant says only Ollama models that support tools may control Home Assistant, so a model without tool support can answer questions but cannot act on devices.
“Only models that support Tools may control Home Assistant.” (Controlling Home Assistant)