Instructions to use immortaltatsu/ghost-ai-pro-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use immortaltatsu/ghost-ai-pro-gguf 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 immortaltatsu/ghost-ai-pro-gguf:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf immortaltatsu/ghost-ai-pro-gguf:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf immortaltatsu/ghost-ai-pro-gguf:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf immortaltatsu/ghost-ai-pro-gguf:Q4_K_S

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 immortaltatsu/ghost-ai-pro-gguf:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf immortaltatsu/ghost-ai-pro-gguf:Q4_K_S

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 immortaltatsu/ghost-ai-pro-gguf:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf immortaltatsu/ghost-ai-pro-gguf:Q4_K_S

Use Docker

docker model run hf.co/immortaltatsu/ghost-ai-pro-gguf:Q4_K_S

LM Studio
Jan

vLLM

How to use immortaltatsu/ghost-ai-pro-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "immortaltatsu/ghost-ai-pro-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "immortaltatsu/ghost-ai-pro-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/immortaltatsu/ghost-ai-pro-gguf:Q4_K_S

Ollama
How to use immortaltatsu/ghost-ai-pro-gguf with Ollama:
```
ollama run hf.co/immortaltatsu/ghost-ai-pro-gguf:Q4_K_S
```

Unsloth Studio

How to use immortaltatsu/ghost-ai-pro-gguf 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 immortaltatsu/ghost-ai-pro-gguf 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 immortaltatsu/ghost-ai-pro-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for immortaltatsu/ghost-ai-pro-gguf to start chatting

How to use immortaltatsu/ghost-ai-pro-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf immortaltatsu/ghost-ai-pro-gguf:Q4_K_S

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": "immortaltatsu/ghost-ai-pro-gguf:Q4_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use immortaltatsu/ghost-ai-pro-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf immortaltatsu/ghost-ai-pro-gguf:Q4_K_S

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 immortaltatsu/ghost-ai-pro-gguf:Q4_K_S

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use immortaltatsu/ghost-ai-pro-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf immortaltatsu/ghost-ai-pro-gguf:Q4_K_S

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 "immortaltatsu/ghost-ai-pro-gguf:Q4_K_S" \
  --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 immortaltatsu/ghost-ai-pro-gguf with Docker Model Runner:
```
docker model run hf.co/immortaltatsu/ghost-ai-pro-gguf:Q4_K_S
```

Lemonade

How to use immortaltatsu/ghost-ai-pro-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull immortaltatsu/ghost-ai-pro-gguf:Q4_K_S

Run and chat with the model

lemonade run user.ghost-ai-pro-gguf-Q4_K_S

List all available models

lemonade list

Ghost AI Pro

On-device financial intelligence — built for Ghost AI on Solana.

Ghost AI Pro is part of Ghost AI, an on-device privacy-first crypto application running on Solana. The model powers private, local AI features inside the Ghost AI app — your prompts, wallet context, and financial data never leave your device.

Ghost AI Pro is a fork of LiquidAI's LFM 2.5 (1.2B Instruct), rebranded and packaged for on-device financial use cases. All underlying model weights, architecture, and capabilities derive from LFM 2.5 — credit and licensing terms remain with the upstream project.

Ghost AI Pro is a compact, quantized language model engineered to run privately on consumer hardware — phones, laptops, edge devices — without sending a single token to the cloud. It is purpose-tuned for the financial domain: portfolio reasoning, market commentary, statement parsing, expense categorization, on-chain activity summarization, and conversational assistance for personal, professional, and crypto-native finance workflows.

For ultra-light deployments (mobile, embedded), see the smaller Ghost AI (350M, Q6_K, ~280MB).

Ghost AI model family

Tier	Repo	Base	Quantization	Size	Best for
Ghost AI	`immortaltatsu/ghost-ai-gguf`	LFM 2.5 350M	Q6_K	~280 MB	Mobile, embedded, instant responses
Ghost AI Pro (this)	`immortaltatsu/ghost-ai-pro-gguf`	LFM 2.5 1.2B Instruct	Q4_K_S	~700 MB	Desktop, deeper reasoning

Why Ghost AI Pro

On-device, always private. Runs locally via llama.cpp, LM Studio, Ollama, or any GGUF-compatible runtime. Your prompts, wallet data, and financial context never leave your device.
Built for finance + crypto. Optimized prompting and behavior around budgeting, markets, accounting concepts, on-chain transactions, and personal-finance reasoning.
Native to Ghost AI on Solana. Powers the local AI surface of the Ghost AI app — a privacy-first crypto experience on the Solana blockchain.
Lean footprint. Q4_K_S quantization — ~700MB on disk, comfortable on 4GB+ RAM devices.
Fast inference. Designed for real-time, low-latency interaction on CPU and consumer GPU.

Files

File	Quantization	Size	Notes
`ghost-ai-pro-Q4_K_S.gguf`	Q4_K_S	~700 MB	Recommended default. Best balance of quality and footprint for on-device use.

Usage

llama.cpp

./llama-cli -m ghost-ai-pro-Q4_K_S.gguf -p "Summarize this quarter's spending: ..." -n 256

Ollama (Modelfile)

FROM ./ghost-ai-pro-Q4_K_S.gguf
PARAMETER temperature 0.7
PARAMETER num_ctx 4096

ollama create ghost-ai-pro -f Modelfile
ollama run ghost-ai-pro

LM Studio

Download the .gguf file and load it directly from the LM Studio model browser.

Intended Use

Ghost AI Pro is intended for:

Powering the on-device AI layer of the Ghost AI crypto app on Solana
Private wallet, transaction, and portfolio explanations
Personal finance assistants and budgeting copilots
On-device document Q&A over statements, invoices, and reports
Lightweight market, DeFi, and economic commentary generation
Embedded assistants in fintech and crypto apps where privacy is non-negotiable

Limitations

Ghost AI Pro is a small model. It is not a substitute for licensed financial advice, accounting, or legal counsel, and it is not a trading or transaction-signing agent. Verify any numerical reasoning, dates, ticker symbols, token addresses, on-chain claims, and regulatory statements against authoritative sources before acting on them. Always confirm wallet operations through the Ghost AI app's signing flow — never from raw model output.

About Ghost AI

Ghost AI is an on-device, privacy-first crypto app built on Solana. It brings local AI directly into the wallet experience — letting users explore transactions, balances, and DeFi context with a model that runs entirely on their own device. Nothing is logged, sent to a server, or shared with a third party.

Ghost AI Pro is the model that powers this on-device intelligence layer.

Upstream

Ghost AI Pro is a fork of LiquidAI/LFM2.5-1.2B-Instruct. The GGUF quantizations are sourced from unsloth/LFM2.5-1.2B-Instruct-GGUF.

License

Released for research and on-device application use. This model is governed by the upstream LFM Open License issued by Liquid AI — please review the original terms before redistribution or commercial deployment.

Ghost AI Pro — intelligence that stays with you.

Downloads last month: 11

GGUF

Model size

1B params

Architecture

lfm2

Hardware compatibility

4-bit

Model tree for immortaltatsu/ghost-ai-pro-gguf

Base model

LiquidAI/LFM2.5-1.2B-Base

Finetuned

LiquidAI/LFM2.5-1.2B-Instruct

Quantized

(73)

this model