Instructions to use RMDWLLC/Jah-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RMDWLLC/Jah-1.0 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RMDWLLC/Jah-1.0",
	filename="GLM-5.2-REAP50-Q3_K_M-00001-of-00005.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use RMDWLLC/Jah-1.0 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RMDWLLC/Jah-1.0:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf RMDWLLC/Jah-1.0:Q3_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RMDWLLC/Jah-1.0:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf RMDWLLC/Jah-1.0:Q3_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf RMDWLLC/Jah-1.0:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf RMDWLLC/Jah-1.0:Q3_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf RMDWLLC/Jah-1.0:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RMDWLLC/Jah-1.0:Q3_K_M

Use Docker

docker model run hf.co/RMDWLLC/Jah-1.0:Q3_K_M

LM Studio
Jan
Ollama
How to use RMDWLLC/Jah-1.0 with Ollama:
```
ollama run hf.co/RMDWLLC/Jah-1.0:Q3_K_M
```

Unsloth Studio

How to use RMDWLLC/Jah-1.0 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RMDWLLC/Jah-1.0 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RMDWLLC/Jah-1.0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RMDWLLC/Jah-1.0 to start chatting

How to use RMDWLLC/Jah-1.0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RMDWLLC/Jah-1.0:Q3_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "RMDWLLC/Jah-1.0:Q3_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use RMDWLLC/Jah-1.0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RMDWLLC/Jah-1.0:Q3_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default RMDWLLC/Jah-1.0:Q3_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use RMDWLLC/Jah-1.0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RMDWLLC/Jah-1.0:Q3_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "RMDWLLC/Jah-1.0:Q3_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use RMDWLLC/Jah-1.0 with Docker Model Runner:
```
docker model run hf.co/RMDWLLC/Jah-1.0:Q3_K_M
```

Lemonade

How to use RMDWLLC/Jah-1.0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RMDWLLC/Jah-1.0:Q3_K_M

Run and chat with the model

lemonade run user.Jah-1.0-Q3_K_M

List all available models

lemonade list

Jah 1.0

Jah is the private AI that powers Echols — 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.

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:

# 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

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

Downloads last month: 11

GGUF

Model size

381B params

Architecture

glm-dsa

Hardware compatibility

3-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support