README.md

metadata

title: TARX
emoji: 🖥️
colorFrom: blue
colorTo: gray
sdk: static
pinned: false

TARX

Local-first AI that belongs to you.

We build AI infrastructure that runs on your machine. Your conversations never leave your device.

What We're Building

TARX is inverting AI. From centralized to distributed. From extraction to participation. From users as products to users as owners.

• Local Inference: TX models optimized for consumer hardware
• Mesh Network: Distributed supercomputer owned by users
• Zero Surveillance: We can't see your data because we never receive it

Models

Model	Parameters	RAM Required	Best For
TX-8G	7B	8 GB	General use, most users
TX-12G	12B	12 GB	Complex reasoning, code
TX-16G	14B	16 GB	Maximum capability

Quick Start

# Download TARX Desktop (includes models)
# macOS, Windows, Linux
https://tarx.com/download

Or use models directly:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Tarxxxxxx/TX-8G")
tokenizer = AutoTokenizer.from_pretrained("Tarxxxxxx/TX-8G")

Links

• 🌐 Website
• 📖 Documentation
• 📥 Download
• 🐦 Twitter/X
• 💼 LinkedIn

About

TARX is building the protocol for decentralized AI. Designed by John Wantz Jr., In Austin Texas in the United States of America.

This is infrastructure, not a chatbot wrapper.

---

Your AI. Your machine. Your data.