🚀 EDDI 6.5.0

19 LLM providers, knowledge bases that crawl your site and read your files, and conversations that follow compatible agent versionsWhat's new

Managed Cloud Get Started
All models
MicrosoftRuns locally

Phi-4-mini

Microsoft's 3.8B open model for memory-constrained, latency-sensitive work and maths and logic reasoning.

Run It in EDDIVendor documentation ↗

Strengths

  • Runs in constrained environments
  • Maths and logic
  • Function calling
  • MIT license

Best For

  • Local and edge inference
  • Latency-sensitive apps
  • Light tool calling

Run It in EDDI

The fastest route is the Manager: open the agent wizard or the Platform Operator and pick the provider and model. To configure it yourself, follow these steps for the provider you want.

Ollama (local) · type: "ollama"

Model ids: phi4-mini

1. Store the credential

This provider does not use an API key: Ollama needs no key. Point baseUrl at your Ollama server; with EDDI's Ollama overlay it is http://ollama:11434.

2. Configure the LLM task

Use this as the langchain.json of the agent's workflow, or paste the parameters into the LLM editor in the Manager.

{
  "tasks": [
    {
      "actions": [
        "send_message"
      ],
      "id": "chat",
      "type": "ollama",
      "parameters": {
        "baseUrl": "http://ollama:11434",
        "model": "phi4-mini",
        "timeout": "120000",
        "systemMessage": "You are a helpful assistant",
        "addToOutput": "true"
      }
    }
  ]
}

Notes for EDDI

  • Runs fully offline once the model is downloaded, so it suits air-gapped deployments.

Related Models

GoogleGemma (Gemma 4, Gemma 3)Google's open-weight family, from edge-sized models to a 31B dense and a 26B mixture-of-experts model in Gemma 4.MetaLlama 3.2 1BA 1.2B-parameter multilingual model for constrained and on-device environments, small enough to run inside the EDDI JVM.Mistral AIMinistral 3 (3B, 8B, 14B)Small open-weight models in three sizes, each with base, instruct and reasoning variants and image understanding, for local and edge use.

Sources

The facts on this page come from the vendor's documentation, checked on 2026-09-30. Models change quickly, so confirm limits with the vendor before you rely on them. Prices are not listed here: see the vendor's pricing page.

Vendor documentation ↗