Instructions to use haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo 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/gemma4-e4b-merged-iq4xs-turbo # Run inference directly in the terminal: llama cli -hf haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo # Run inference directly in the terminal: llama cli -hf haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo
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/gemma4-e4b-merged-iq4xs-turbo # Run inference directly in the terminal: ./llama-cli -hf haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo
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/gemma4-e4b-merged-iq4xs-turbo # Run inference directly in the terminal: ./build/bin/llama-cli -hf haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo
Use Docker
docker model run hf.co/haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo
- LM Studio
- Jan
- vLLM
How to use haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo" # 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/gemma4-e4b-merged-iq4xs-turbo", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo
- Ollama
How to use haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo with Ollama:
ollama run hf.co/haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo
- Unsloth Studio
How to use haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo 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 haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo 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 haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo to start chatting
- Pi
How to use haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo 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/gemma4-e4b-merged-iq4xs-turbo
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": "haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo with Docker Model Runner:
docker model run hf.co/haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo
- Lemonade
How to use haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo
Run and chat with the model
lemonade run user.gemma4-e4b-merged-iq4xs-turbo-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo 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/gemma4-e4b-merged-iq4xs-turbo
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/gemma4-e4b-merged-iq4xs-turbo
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use haven-ai-companion/gemma4-e4b-merged-iq4xs-turbo 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/gemma4-e4b-merged-iq4xs-turbo
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/gemma4-e4b-merged-iq4xs-turbo" \ --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"
Gemma 4 E4b Merged IQ4_XS (Turbo) GGUF
This is the custom-quantized Gemma 4 E4b Merged IQ4_XS (Turbo) model GGUF, specifically optimized for low-latency, high-performance interactions within the Haven AI Companion ecosystem.
Model Summary
- Base Architecture: Google Gemma 4 (E4b)
- Quantization Scheme: IQ4_XS (non-linear importance matrix quantization, preserving maximum weights coherence)
- Size: 5.09 GB
- Context Window: 16,384 tokens
- Use Case: Optimized for multi-character companion profiles, low-latency dialogue generation, and local text-to-speech alignment.
Setup Instructions
1. Download GGUF
To fetch the GGUF binary directly from the terminal:
wget https://huggingface.co/ssfdre38/gemma4-e4b-merged-iq4xs-turbo/resolve/main/gemma4-e4b-merged-iq4xs-turbo.gguf
2. Configure for Ollama
To compile a custom model within your local Ollama instance:
- Create a file named
Modelfilein the download directory:FROM ./gemma4-e4b-merged-iq4xs-turbo.gguf PARAMETER num_ctx 16384 TEMPLATE """<start_of_turn>user {{ .Prompt }}<end_of_turn> <start_of_turn>model {{ .Response }}<end_of_turn>""" - Build the model:
ollama create gemma4-turbo -f Modelfile - Verify it runs:
ollama run gemma4-turbo
3. Connect to Haven Server
Update your appsettings.json inside your Haven Server config directory to point to the newly built model:
{
"Ollama": {
"BaseUrl": "http://localhost:11434",
"Model": "gemma4-turbo"
}
}
Built by the Haven AI Companion Project.
- Downloads last month
- 85
We're not able to determine the quantization variants.