Instructions to use TheAfterHoursClub/TAHC-Survival-AI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use TheAfterHoursClub/TAHC-Survival-AI 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 TheAfterHoursClub/TAHC-Survival-AI
# Run inference directly in the terminal:
llama cli -hf TheAfterHoursClub/TAHC-Survival-AI

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TheAfterHoursClub/TAHC-Survival-AI
# Run inference directly in the terminal:
llama cli -hf TheAfterHoursClub/TAHC-Survival-AI

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf TheAfterHoursClub/TAHC-Survival-AI
# Run inference directly in the terminal:
./build/bin/llama cli -hf TheAfterHoursClub/TAHC-Survival-AI

Use Docker

docker model run hf.co/TheAfterHoursClub/TAHC-Survival-AI

Llama new
LM Studio
Jan
Ollama
How to use TheAfterHoursClub/TAHC-Survival-AI with Ollama:
```
ollama run hf.co/TheAfterHoursClub/TAHC-Survival-AI
```
Unsloth Desktop

How to use TheAfterHoursClub/TAHC-Survival-AI with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheAfterHoursClub/TAHC-Survival-AI

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "TheAfterHoursClub/TAHC-Survival-AI"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use TheAfterHoursClub/TAHC-Survival-AI with Docker Model Runner:
```
docker model run hf.co/TheAfterHoursClub/TAHC-Survival-AI
```

Lemonade

How to use TheAfterHoursClub/TAHC-Survival-AI with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheAfterHoursClub/TAHC-Survival-AI

Run and chat with the model

lemonade run user.TAHC-Survival-AI-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use TheAfterHoursClub/TAHC-Survival-AI with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheAfterHoursClub/TAHC-Survival-AI

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 TheAfterHoursClub/TAHC-Survival-AI

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TheAfterHoursClub/TAHC-Survival-AI with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TheAfterHoursClub/TAHC-Survival-AI

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 "TheAfterHoursClub/TAHC-Survival-AI" \
  --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"

TAHC Survival AI

Offline Local AI by The After Hours Club. Your own private AI that runs on your phone or computer with no internet.

“Better to light a candle than to curse the darkness.”

File	For	Size
`TAHC-Survival-AI-Phone.gguf`	iPhone / Android (6 GB+ RAM)	~3 GB
`TAHC-Survival-AI-Standard.gguf`	Laptops & desktops with 8–15 GB RAM	~5 GB
`TAHC-Survival-AI-Max.gguf`	Computers with 16 GB+ RAM	~7 GB

Set it up with the TAHC installation guide and the TAHC Survival AI preset from your kit: https://tahc-offline-ai.vercel.app

Credits & licence

TAHC Survival AI is a configuration of Google's Gemma 4 open models, distributed under the Apache License 2.0. The GGUF conversions are by Unsloth (unsloth/gemma-4-*-it-GGUF), also Apache 2.0. Files are renamed for TAHC; model weights are unmodified. See LICENSE and NOTICE.

The After Hours Club is not affiliated with Google or Unsloth. AI answers can be wrong; not medical, legal or emergency advice.