Llama Cpp Basic

Run a local GGUF model with LlamaCpp and print sync and streamed responses.

basic.py

"""
Llama Cpp Basic
===============

Cookbook example for `llama_cpp/basic.py`.
"""

from agno.agent import Agent, RunOutput  # noqa
from agno.models.llama_cpp import LlamaCpp

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

agent = Agent(model=LlamaCpp(id="ggml-org/gpt-oss-20b-GGUF"), markdown=True)

# Get the response in a variable
# run: RunOutput = agent.run("Share a 2 sentence horror story")
# print(run.content)

# Print the response in the terminal

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # --- Sync ---
    agent.print_response("Share a 2 sentence horror story")

    # --- Sync + Streaming ---
    agent.print_response("Share a 2 sentence horror story", stream=True)

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno openai
   
3. Install llama.cpp

   Install the llama-server binary. This command supports macOS and Linux with Homebrew; see the llama.cpp installation guide for other platforms:

   brew install llama.cpp
   
4. Start llama.cpp

   Serve ggml-org/gpt-oss-20b-GGUF at http://127.0.0.1:8080/v1:

   llama-server -hf ggml-org/gpt-oss-20b-GGUF --ctx-size 0 --jinja -ub 2048 -b 2048
   
5. Run the example

   Save the code above as basic.py, then run:

   python basic.py
   

Full source: cookbook/90_models/llama_cpp/basic.py