9 3 days ago

A lightweight, CPU-optimized LLM tailored for Linux command-line environments. Built specifically for low-resource hardware, shell-based workflows, and rapid CLI task execution without requiring dedicated GPU acceleration.

tools
ollama run igorcruz/fedora

Applications

Claude Code
Claude Code ollama launch claude --model igorcruz/fedora
OpenCode
OpenCode ollama launch opencode --model igorcruz/fedora
Hermes Agent
Hermes Agent ollama launch hermes --model igorcruz/fedora
OpenClaw
OpenClaw ollama launch openclaw --model igorcruz/fedora

Models

View all →

1 model

fedora:latest

2.0GB · 128K context window · Text · 3 days ago

Readme

Model Overview: igorcruz/fedora

  • Base Model: Llama 3.2 (llama3.2)
  • System Persona: Configured with a custom system prompt: “You are a friendly assistant.”
  • Target Audience: Linux command-line users seeking a friendly local AI assistant via terminal.
  • Registry: Published and available on Ollama Hub under igorcruz/fedora.

Quick CLI Execution

To download and run this custom model directly in your Linux terminal:

ollama run igorcruz/fedora


Build & Release Workflow

  1. Base Model Fetch: Pulled official llama3.2 weights from the Ollama library.
  2. Modelfile Definition: Created a customized Modelfile setting llama3.2 as the parent image and defining the system persona.
  3. Local Build: Compiled the customized image binary using ollama create -f Modelfile igorcruz/fedora.
  4. Cloud Publish: Pushed the finalized model tag igorcruz/fedora to the remote Ollama model library for public accessibility.