Ollama

Run Large Language Models locally with Ollama Ollama is a fantastic tool for running models locally. Ollama supports multiple open-source models. See the library here. We recommend experimenting to find the best-suited model for your use-case. Here are some general recommendations:

llama3.3 models are good for most basic use-cases.
qwen models perform specifically well with tool use.
deepseek-r1 models have strong reasoning capabilities.
phi4 models are powerful, while being really small in size.

Set up a model

Install ollama and run a model using

run model

ollama run llama3.1

This gives you an interactive session with the model. Alternatively, to download the model to be used in an Agno agent

pull model

ollama pull llama3.1

Example

After you have the model locally, use the Ollama model class to access it

from agno.agent import Agent, RunResponse
from agno.models.ollama import Ollama

agent = Agent(
    model=Ollama(id="llama3.1"),
    markdown=True
)

# Print the response in the terminal
agent.print_response("Share a 2 sentence horror story.")

View more examples here.

Params

Parameter	Type	Default	Description
`id`	`str`	`"llama3.1"`	The ID of the model to use.
`name`	`str`	`"Ollama"`	The name of the model.
`provider`	`str`	`"Ollama"`	The provider of the model.
`format`	`Optional[Any]`	`None`	The format of the response.
`options`	`Optional[Any]`	`None`	Additional options to pass to the model.
`keep_alive`	`Optional[Union[float, str]]`	`None`	The keep alive time for the model.
`request_params`	`Optional[Dict[str, Any]]`	`None`	Additional parameters to pass to the request.
`host`	`Optional[str]`	`None`	The host to connect to.
`timeout`	`Optional[Any]`	`None`	The timeout for the connection.
`client_params`	`Optional[Dict[str, Any]]`	`None`	Additional parameters to pass to the client.
`client`	`Optional[OllamaClient]`	`None`	A pre-configured instance of the Ollama client.
`async_client`	`Optional[AsyncOllamaClient]`	`None`	A pre-configured instance of the asynchronous Ollama client.
`structured_outputs`	`bool`	`False`	Whether to use the structured outputs with this Model.
`supports_structured_outputs`	`bool`	`True`	Whether the Model supports structured outputs.

Ollama is a subclass of the Model class and has access to the same params.

Introduction

Concepts

Other

How to

Set up a model

Example

Params

​Set up a model

​Example

​Params

Set up a model

Example

Params