---
license: mit
library_name: gguf
tags:
  - private-ai
  - sovereign-ai
  - rmdw
  - echols
  - jah
language:
  - en
---

# Jah 1.0

**Jah is the private AI that powers [Echols](https://echols.ai) — RMDW's private alternative to ChatGPT and Claude.** It runs entirely on hardware RMDW owns and controls. Nothing you type leaves to a third-party cloud, nothing is stored externally, and nothing is ever used to train another company's model. What you bring to Jah stays yours.

This is not a chatbot demo. Jah is the brain of a full private-AI product that people pay for and use every day.

## What Jah does

- **Private chat** with live, interactive artifacts (apps, charts, dashboards, diagrams), persistent memory, web search with citations, and in-browser code execution.
- **Builds real apps.** Describe what you want and Jah writes a complete project, pushes it to **your own GitHub**, and deploys it to a **live URL** you can share — from a single sentence. You own the code.
- **Image and video** generation.
- **Agentic.** Acts across your connected accounts (Gmail, Calendar, Telegram) on your behalf.

All of it private, for **$25/mo** — a fraction of what the cloud labs charge for less. Try it at **[echols.ai](https://echols.ai)**.

## Why it exists

The best assistants from the big labs run $100–$200 a month and still send everything you type to their servers. Jah is the opposite bet: a genuinely capable assistant that runs on infrastructure you can see and trust, at a price built for everyone. Privacy here isn't a setting you toggle — it's the architecture.

## Run it yourself

The weights are open, because owning your AI end-to-end should be possible. Serve Jah on your own GPU with `llama.cpp`:

```bash
# point --model at the first GGUF shard you downloaded
llama-server --model jah-00001-of-NNNNN.gguf \
  -ngl 999 -c 32768 -fa on --jinja \
  --host 0.0.0.0 --port 8080
```

**Tip:** for one-shot generation, disable reasoning so the full token budget goes to the answer — pass `"chat_template_kwargs": {"enable_thinking": false}` in your request. A ready-to-run Ollama `Modelfile` is included in this repo.

## The bigger idea

Most AI today is *rented* from a handful of companies. Jah is *owned* — a private model running a real product on hardware RMDW controls, with open weights so anyone can do the same. That is the future RMDW is building: **AI you own, not AI you rent.** → **[rmdw.ai](https://rmdw.ai)**

---

*Jah 1.0 — RMDW LLC. Private AI, run on your terms.*