Ollama

Run local Ollama models with the same generation APIs as cloud providers.

OllamaModel defaults to http://localhost:11434/v1 and needs no key.

let model = OllamaModel("gemma4")
let result = streamText(model: model, prompt: "Say hello.")

for try await text in result.textStream {
  print(text, terminator: "")
}

Override baseURL: when Ollama runs on another host. Models that emit inline <think> blocks can use the reasoning extraction middleware. On iOS, enable NSAllowsLocalNetworking so the simulator can reach your Mac.

Models

Current library examples include gemma4, qwen3-coder-next, deepseek-v4-flash, and kimi-k2.7-code. The usable IDs are the models installed locally; inspect them with ollama list or:

curl http://localhost:11434/api/tags

Browse the live Ollama model library to find and pull additional models.

On this page