Skip to content

Using Local AI Models

The AI Assistant can connect to locally hosted AI models instead of cloud services. This offers several advantages:

  • Privacy — Your project data never leaves your machine
  • No API costs — Run as many queries as you want for free
  • Offline use — Works without an internet connection
  • Full control — Choose and customize your own models
SoftwareProvider SettingDefault HostDefault Port
OllamaOllamalocalhost11434
LM StudioLlamaCpplocalhost1234
llama.cpp serverLlamaCpplocalhost8080

Ollama is the easiest way to run local AI models on your machine.

  1. Install Ollama

    Download and install Ollama from ollama.com.

  2. Pull a model

    Open a terminal and download a model that supports function calling:

    Terminal window
    ollama pull llama3
  3. Configure Paquet Builder

    • Open the AI Settings dialog in Paquet Builder
    • Select Ollama as the provider
    • The default host (localhost) and port (11434) work automatically
    • Enter the model name (e.g., llama3) in the Model field
  4. Start chatting

    The AI Assistant will connect to your local Ollama instance. Ollama starts automatically when a request is received.

For the AI Assistant’s function calling (tool use) to work properly, the model must support structured tool calls. Here are recommended models:

ModelSizeFunction CallingNotes
Llama 3 (8B)~5 GBGoodBest balance of speed and capability
Llama 3 (70B)~40 GBVery GoodRequires 48+ GB RAM or powerful GPU
Qwen 2.5 (7B)~4 GBGoodStrong tool use, fast inference
Mistral (7B)~4 GBGoodReliable function calling

If your local AI server runs on a different machine or a custom port:

  1. Open AI Settings

  2. Modify the Host field (e.g., 192.168.1.100 for a server on your local network)

  3. Modify the Port field as needed

You can switch between local and cloud providers at any time by changing the provider in AI Settings. A practical approach is to:

  • Use a local model for quick, simple tasks (changing a setting, listing components)
  • Switch to a cloud provider for complex tasks (building custom action workflows, full project setup)