Mallama 🦙

Mallama is a lightweight, self-hosted web UI for running local LLMs with Ollama.
It’s designed to be simple, fast, and hackable. No cloud. No accounts. Your models, your machine.

---

✨ Features

• 🖥️ Clean web-based chat interface
• 🔌 Uses local Ollama models (no external APIs)
• ⚡ Fast startup, minimal dependencies
• 🧠 Model selection directly from the UI
• 🧪 Designed for experimentation and extension
• 🐧 Linux-friendly, self-hosted by default

---

🚀 Quick Start

Requirements

• Python 3.9+
• Ollama installed and running

Run locally

git clone https://github.com/mesut2ooo/mallama.git
cd mallama

or

pip install -r requirements.txt
python app.py

Then open your browser at: http://127.0.0.1:5000

That’s it.

---

🎯 Why Mallama? Most local LLM UIs are either: Overly complex Heavy on resources Hard to modify Mallama aims to be: Easy to understand Easy to modify Easy to run on modest hardware It’s built for developers, tinkerers, and self-hosting enthusiasts.

---

🐛 Feedback & Contributions This project is actively looking for feedback. Found a bug? Open an issue. Have an idea? Start a discussion. Want to contribute? PRs are welcome. If something feels awkward, slow, or confusing — that’s valuable feedback.