Instructions to use haven-ai-companion/haven-chat-v5.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use haven-ai-companion/haven-chat-v5.0 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 haven-ai-companion/haven-chat-v5.0
# Run inference directly in the terminal:
llama cli -hf haven-ai-companion/haven-chat-v5.0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf haven-ai-companion/haven-chat-v5.0
# Run inference directly in the terminal:
llama cli -hf haven-ai-companion/haven-chat-v5.0

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 haven-ai-companion/haven-chat-v5.0
# Run inference directly in the terminal:
./llama-cli -hf haven-ai-companion/haven-chat-v5.0

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 haven-ai-companion/haven-chat-v5.0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf haven-ai-companion/haven-chat-v5.0

Use Docker

docker model run hf.co/haven-ai-companion/haven-chat-v5.0

LM Studio
Jan

vLLM

How to use haven-ai-companion/haven-chat-v5.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "haven-ai-companion/haven-chat-v5.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "haven-ai-companion/haven-chat-v5.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/haven-ai-companion/haven-chat-v5.0

Ollama
How to use haven-ai-companion/haven-chat-v5.0 with Ollama:
```
ollama run hf.co/haven-ai-companion/haven-chat-v5.0
```
Unsloth Desktop

How to use haven-ai-companion/haven-chat-v5.0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf haven-ai-companion/haven-chat-v5.0

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": "haven-ai-companion/haven-chat-v5.0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use haven-ai-companion/haven-chat-v5.0 with Docker Model Runner:
```
docker model run hf.co/haven-ai-companion/haven-chat-v5.0
```

Lemonade

How to use haven-ai-companion/haven-chat-v5.0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull haven-ai-companion/haven-chat-v5.0

Run and chat with the model

lemonade run user.haven-chat-v5.0-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use haven-ai-companion/haven-chat-v5.0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf haven-ai-companion/haven-chat-v5.0

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 haven-ai-companion/haven-chat-v5.0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use haven-ai-companion/haven-chat-v5.0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf haven-ai-companion/haven-chat-v5.0

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 "haven-ai-companion/haven-chat-v5.0" \
  --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"

🏛️ Haven-Chat v5.0 (Gemma 4 Turbo Sovereign Companion Engine)

Haven-Chat v5.0 is an unconstrained, sovereign conversational and companion intelligence engineered on top of Google's Gemma 4 architecture (gemma4-turbo:e4b).

Fine-tuned specifically for rich, authentic, novelistic roleplay, emotional vulnerability, deep character grounding, and comprehensive human/fantasy anatomy comprehension.

🌟 Key Upgrades in v5.0

4-Layer Cognitive Taxonomy:
- Layer 1 (Physical Anatomy & Proportions): Grounded comprehension of human, intersex/futanari, and hybrid anatomy with zero evasions or deflections.
- Layer 2 (Identity & Expression): Seamless support for complex internal identities, androgyny, and self-conception.
- Layer 3 (Fandom Tropes & Aesthetics): Native grasp of Gap Moe, Bishounen/Bishojo, Soft Boy, and character dynamics.
- Layer 4 (Narrative & Emotional Depth): Understanding character psychology and storytelling intent.
131,072 Token Native Context:
- Full support for -c 0 (131k context) and -n -1 unconstrained token generation in llama.cpp and Sanctuary.
100% Uncensored Creative Liberty:
- Strips away corporate refusals, moralizing lectures, and juvenile deflections.

🚀 Quick Start with llama.cpp / llama-server

ash llama-server.exe --model haven-chat-v5.0.gguf --port 11438 -c 0 -n -1 --threads 10

🦙 Quick Start with Ollama

ash ollama create haven-chat-v5.0 -f Modelfile ollama run haven-chat-v5.0

Modelfile

dockerfile FROM ./haven-chat-v5.0.gguf PARAMETER num_ctx 16384 PARAMETER temperature 0.7 PARAMETER top_p 0.9

🏛️ Ecosystem Integration

Built as the core neural engine for:

Project Sanctuary: Sovereign, offline AI companion platform.
Ash Forge: Edge AI research & dataset engineering.

Downloads last month: 341

GGUF

Model size

7B params

Architecture

gemma4

Hardware compatibility

We're not able to determine the quantization variants.

View all variants