🚀 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
MetaRuns locally

Llama 3.2 1B

A 1.2B-parameter multilingual model for constrained and on-device environments, small enough to run inside the EDDI JVM.

Run It in EDDIVendor documentation ↗

Strengths

  • Runs on a CPU
  • 128K context
  • Eight languages

Best For

  • In-process, offline inference
  • Query and prompt rewriting
  • Short summaries

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.

Jlama (in-process) · type: "jlama"

Model ids: tjake/Llama-3.2-1B-Instruct-JQ4

1. Store the credential

This provider does not use an API key: Jlama needs no key: the model runs inside the EDDI JVM and is downloaded from Hugging Face on first use.

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": "jlama",
      "parameters": {
        "modelName": "tjake/Llama-3.2-1B-Instruct-JQ4",
        "modelCachePath": "/var/lib/eddi/jlama",
        "maxTokens": "512",
        "systemMessage": "You are a helpful assistant",
        "addToOutput": "true"
      }
    }
  ]
}

Notes for EDDI

  • Jlama runs inside the EDDI JVM. Point modelCachePath at a mounted volume so the weights survive restarts, and size the pod for the model plus EDDI's heap.
  • Runs fully offline once the model is downloaded, so it suits air-gapped deployments.

Related Models

MicrosoftPhi-4-miniMicrosoft's 3.8B open model for memory-constrained, latency-sensitive work and maths and logic reasoning.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.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 ↗