Instructions to use Tinman-Lab/Tinman-gemma4-companion-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tinman-Lab/Tinman-gemma4-companion-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Tinman-Lab/Tinman-gemma4-companion-gguf",
	filename="gemma4-companion-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Tinman-Lab/Tinman-gemma4-companion-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Tinman-Lab/Tinman-gemma4-companion-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Tinman-Lab/Tinman-gemma4-companion-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Tinman-Lab/Tinman-gemma4-companion-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Tinman-Lab/Tinman-gemma4-companion-gguf: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 Tinman-Lab/Tinman-gemma4-companion-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Tinman-Lab/Tinman-gemma4-companion-gguf: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 Tinman-Lab/Tinman-gemma4-companion-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Tinman-Lab/Tinman-gemma4-companion-gguf:Q4_K_M

Use Docker

docker model run hf.co/Tinman-Lab/Tinman-gemma4-companion-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use Tinman-Lab/Tinman-gemma4-companion-gguf with Ollama:
```
ollama run hf.co/Tinman-Lab/Tinman-gemma4-companion-gguf:Q4_K_M
```

Unsloth Studio new

How to use Tinman-Lab/Tinman-gemma4-companion-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 Tinman-Lab/Tinman-gemma4-companion-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 Tinman-Lab/Tinman-gemma4-companion-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Tinman-Lab/Tinman-gemma4-companion-gguf to start chatting

Pi new

How to use Tinman-Lab/Tinman-gemma4-companion-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Tinman-Lab/Tinman-gemma4-companion-gguf: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": "Tinman-gemma4-companion-gguf"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Tinman-Lab/Tinman-gemma4-companion-gguf with Docker Model Runner:
```
docker model run hf.co/Tinman-Lab/Tinman-gemma4-companion-gguf:Q4_K_M
```

Lemonade

How to use Tinman-Lab/Tinman-gemma4-companion-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Tinman-Lab/Tinman-gemma4-companion-gguf:Q4_K_M

Run and chat with the model

lemonade run user.Tinman-gemma4-companion-gguf-Q4_K_M

List all available models

lemonade list

Gemma 4 E4B Companion — GGUF Quantizations

GGUF quantized versions of TinmanLabSL/gemma4-companion-merged.

See the main model card for full details on training, system prompts, and deployment.

Available Quantizations

File	Quant	Size	Quality	Use Case
`gemma4-companion-bf16.gguf`	BF16	14 GB	Lossless	Reference / re-quantization
`gemma4-companion-Q8_0.gguf`	Q8_0	7.5 GB	Near-lossless	Desktop with ample RAM
`gemma4-companion-Q4_K_M.gguf`	Q4_K_M	5.0 GB	Good	Recommended for most users

Usage

llama.cpp

./llama-cli -m gemma4-companion-Q4_K_M.gguf -cnv \
  -p "You are a warm, caring companion..."

LM Studio / GPT4All

Load the GGUF file directly from the UI.

System Prompts

See main model card for companion, roleplay, and assistant mode system prompts.

Downloads last month: 1,573

GGUF

Model size

7B params

Architecture

gemma4

Hardware compatibility

4-bit

8-bit

16-bit

Inference Providers NEW

Any-to-Any

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Tinman-Lab/Tinman-gemma4-companion-gguf

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

OBLITERATUS/gemma-4-E4B-it-OBLITERATED

Finetuned

Tinman-Lab/Tinman-gemma4-companion-merged

Quantized

(1)

this model