Instructions to use Ghasty3/CapriAI2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Ghasty3/CapriAI2 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 Ghasty3/CapriAI2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ghasty3/CapriAI2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ghasty3/CapriAI2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ghasty3/CapriAI2: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 Ghasty3/CapriAI2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Ghasty3/CapriAI2: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 Ghasty3/CapriAI2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ghasty3/CapriAI2:Q4_K_M

Use Docker

docker model run hf.co/Ghasty3/CapriAI2:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use Ghasty3/CapriAI2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ghasty3/CapriAI2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ghasty3/CapriAI2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Ghasty3/CapriAI2:Q4_K_M

Ollama
How to use Ghasty3/CapriAI2 with Ollama:
```
ollama run hf.co/Ghasty3/CapriAI2:Q4_K_M
```
Unsloth Desktop

How to use Ghasty3/CapriAI2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ghasty3/CapriAI2: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": "Ghasty3/CapriAI2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Ghasty3/CapriAI2 with Docker Model Runner:
```
docker model run hf.co/Ghasty3/CapriAI2:Q4_K_M
```

Lemonade

How to use Ghasty3/CapriAI2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ghasty3/CapriAI2:Q4_K_M

Run and chat with the model

lemonade run user.CapriAI2-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Ghasty3/CapriAI2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ghasty3/CapriAI2: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 Ghasty3/CapriAI2:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Ghasty3/CapriAI2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ghasty3/CapriAI2: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 "Ghasty3/CapriAI2: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"

CapriAI2

Unofficial fan fine-tunes of conversational models in the voice of Capri from Cyberpunk: Edgerunners 2. Capri keeps her lively, streetwise humor while aiming to be useful and collaborative. This project is not affiliated with CD PROJEKT RED.

Models

Qwen 3.5 4B

Files are in qwen3.5-4b/:

Qwen3.5-4B.Q6_K.gguf: fine-tuned Q6_K model.
Qwen3.5-4B.BF16-mmproj.gguf: multimodal projector; needed for image input.

Base model: Qwen/Qwen3.5-4B. Apache-2.0; see LICENSE.

Gemma 4 E4B IT

Files are in gemma-4-e4b-it/:

CapriAI2-Gemma-4-E4B-it.Q4_K_M.gguf: fine-tuned Q4_K_M model.
CapriAI2-Gemma-4-E4B-it.BF16-mmproj.gguf: multimodal projector; needed for image input.

Base model: google/gemma-4-E4B-it. The upstream model card lists Apache-2.0; see its terms and model card for applicable conditions.

See gemma-4-e4b-it/README.md for loading notes.

MiniCPM5 2B

Files are in minicpm5-2b/:

CapriAI2-MiniCPM5-2B.Q4_K_M.gguf: fine-tuned Q4_K_M model. MiniCPM5 is text-only; it needs no projector.

Base model: openbmb/MiniCPM5-2B, Apache-2.0. See minicpm5-2b/README.md.

Downloads last month: 347

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

4-bit

6-bit