Instructions to use Ghostfury73/ai-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Ghostfury73/ai-models 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 Ghostfury73/ai-models:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ghostfury73/ai-models:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ghostfury73/ai-models:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ghostfury73/ai-models:Q4_K_M

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 Ghostfury73/ai-models:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Ghostfury73/ai-models:Q4_K_M

Use Docker

docker model run hf.co/Ghostfury73/ai-models:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use Ghostfury73/ai-models with Ollama:
```
ollama run hf.co/Ghostfury73/ai-models:Q4_K_M
```
Unsloth Desktop

How to use Ghostfury73/ai-models with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ghostfury73/ai-models:Q4_K_M

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": "Ghostfury73/ai-models:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Ghostfury73/ai-models with Docker Model Runner:
```
docker model run hf.co/Ghostfury73/ai-models:Q4_K_M
```

Lemonade

How to use Ghostfury73/ai-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ghostfury73/ai-models:Q4_K_M

Run and chat with the model

lemonade run user.ai-models-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Ghostfury73/ai-models with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ghostfury73/ai-models:Q4_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 Ghostfury73/ai-models:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Ghostfury73/ai-models with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ghostfury73/ai-models:Q4_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 "Ghostfury73/ai-models:Q4_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"

Model files

Third-party models in GGUF format. Each file keeps the licence of the model it was made from, listed below. The license field above is other because the files are under different licences.

File	Model	Made by	Licence	Changes
`granite-3.0-3b-a800m-instruct-Q4_0.gguf`	Granite 3.0 3B-A800M Instruct	IBM	Apache-2.0	GGUF, Q4_0 quantization (bartowski)
`parakeet-ultra-0.6b-Q4_K_M.gguf`	Parakeet Ultra, a post-training of NVIDIA parakeet-tdt-0.6b-v3	Moondream, NVIDIA	CC BY 4.0	GGUF, Q4_K_M quantization (Nairod785)
`parakeet-redux-0.6b-TQ1_Q8_0.gguf`	Parakeet Redux, a post-training of NVIDIA parakeet-tdt-0.6b-v3	Moondream, NVIDIA	CC BY 4.0	GGUF, TQ1_Q8_0 quantization (Nairod785)

The only changes are the file format and the weight precision. No file here is under a licence other than the one in its row.

Downloads last month: -

GGUF

Model size

3B params

Architecture

granitemoe

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

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