Instructions to use immortaltatsu/ghostai-v2 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/ghostai-v2 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/ghostai-v2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf immortaltatsu/ghostai-v2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf immortaltatsu/ghostai-v2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf immortaltatsu/ghostai-v2:Q4_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 immortaltatsu/ghostai-v2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf immortaltatsu/ghostai-v2:Q4_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 immortaltatsu/ghostai-v2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf immortaltatsu/ghostai-v2:Q4_K_M

Use Docker

docker model run hf.co/immortaltatsu/ghostai-v2:Q4_K_M

LM Studio
Jan

vLLM

How to use immortaltatsu/ghostai-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "immortaltatsu/ghostai-v2"
# 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/ghostai-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/immortaltatsu/ghostai-v2:Q4_K_M

Ollama
How to use immortaltatsu/ghostai-v2 with Ollama:
```
ollama run hf.co/immortaltatsu/ghostai-v2:Q4_K_M
```

Unsloth Studio

How to use immortaltatsu/ghostai-v2 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/ghostai-v2 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/ghostai-v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for immortaltatsu/ghostai-v2 to start chatting

How to use immortaltatsu/ghostai-v2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf immortaltatsu/ghostai-v2:Q4_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": "immortaltatsu/ghostai-v2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use immortaltatsu/ghostai-v2 with Docker Model Runner:
```
docker model run hf.co/immortaltatsu/ghostai-v2:Q4_K_M
```

Lemonade

How to use immortaltatsu/ghostai-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull immortaltatsu/ghostai-v2:Q4_K_M

Run and chat with the model

lemonade run user.ghostai-v2-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use immortaltatsu/ghostai-v2 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/ghostai-v2: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 immortaltatsu/ghostai-v2:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use immortaltatsu/ghostai-v2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf immortaltatsu/ghostai-v2: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 "immortaltatsu/ghostai-v2: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"

GhostAI v2 (distilled)

Second iteration of the Ghost AI on-device planner/executor, fine-tuned from Qwen3.5-0.8B. Supersedes ghostai-alpha.

What changed vs alpha

	alpha	v2
training data	deterministic templates	teacher-distilled (Qwen3.6-35B-A3B, rejection-sampled)
train rows	918	2,969
unique plan summaries	33 / 400 (8%)	~1,074 / 1,122 (96%)
unique clarify questions	3 / 72 (4%)	343 / 356 (96%)
eval split	25% of rows had a train twin	0% — split on utterance fingerprint
tools exercised	25 / 36	31 / 36

Every plan passed four gates before entering the corpus: scenario contract (intent / must_call / must_not_call / flags), value-moving completeness, Layer-1 deterministic checks, and Layer-2 simulated execution.

Files

File	Size
`ghostai-v2-F16.gguf`	1.4 GB
`ghostai-v2-Q8_0.gguf`	774 MB
`ghostai-v2-Q4_K_M.gguf`	505 MB — mobile target

Built from the epoch-1 checkpoint, not the final one: eval loss rose every epoch (0.2162 → 0.2212 → 0.2403) while accuracy plateaued, so epochs 2–3 only overfit.

Metrics (genuinely held-out split)

epoch	eval_loss	eval_token_acc
1 (shipped)	0.2162	0.9449
2	0.2212	0.9471
3	0.2403	0.9472

Final train loss 0.1843. Eval loss sits above train loss and eval accuracy below train accuracy — the correct direction, and the first time these numbers measure generalization rather than memorization.

Usage

llama-cli -m ghostai-v2-Q4_K_M.gguf -ngl 99 --temp 0 --jinja \
  --chat-template-kwargs '{"enable_thinking":false}' \
  -sys "You are Ghost AI, an on-device mobile crypto assistant. Produce a structured plan JSON matching the v1 schema." \
  -p "swap 2 SOL to USDC"

Use grammar-constrained decoding in production — the plan schema when planning, the tool's own JSON schema when executing. Unconstrained output is not reliably schema-valid.

Note: config.json sets mtp_num_hidden_layers: 0. The base checkpoint's Multi-Token- Prediction head is not carried through, and llama.cpp otherwise expects a 25th block.

Known limitations

Non-SOL transfers do not resolve the token. send 50000 BONK to alice still emits send_sol without a preceding search_token, violating provenance rule 1. The corpus contains correct examples (70/70 of the SPL-transfer plans call search_token) but they are outvoted 38-to-130 in the training split, so the model learned the majority "no lookup" pattern. Being addressed by widening that coverage.
Unrecognised tokens are not clarified. send 10 hood to mystic.seeker guesses a send rather than asking which token is meant. Same cause — only 12 such examples.
5 of 36 tools untrained: add_contact, get_address_balance, get_transaction_detail, prediction_claim, prediction_sell.
Weakest categories in the corpus: planning/private-swap (60%), planning/swap (73%).

Swap completeness is fixed: value-moving swap plans now carry through to execute_swap instead of stopping at the quote.

License

Base model Qwen/Qwen3.5-0.8B is Apache 2.0; that license governs this derivative.

Downloads last month: 228

Safetensors

Model size

0.8B params

Tensor type

BF16

Model tree for immortaltatsu/ghostai-v2

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Quantized

(214)

this model