Instructions to use samuelstolicny/claudie-expert-gemma4-31b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use samuelstolicny/claudie-expert-gemma4-31b 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 samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf samuelstolicny/claudie-expert-gemma4-31b: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 samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf samuelstolicny/claudie-expert-gemma4-31b: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 samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M

Use Docker

docker model run hf.co/samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M

LM Studio
Jan

vLLM

How to use samuelstolicny/claudie-expert-gemma4-31b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "samuelstolicny/claudie-expert-gemma4-31b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "samuelstolicny/claudie-expert-gemma4-31b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M

Ollama
How to use samuelstolicny/claudie-expert-gemma4-31b with Ollama:
```
ollama run hf.co/samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M
```
Unsloth Desktop

How to use samuelstolicny/claudie-expert-gemma4-31b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf samuelstolicny/claudie-expert-gemma4-31b: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": "samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use samuelstolicny/claudie-expert-gemma4-31b with Docker Model Runner:
```
docker model run hf.co/samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M
```

Lemonade

How to use samuelstolicny/claudie-expert-gemma4-31b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M

Run and chat with the model

lemonade run user.claudie-expert-gemma4-31b-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use samuelstolicny/claudie-expert-gemma4-31b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf samuelstolicny/claudie-expert-gemma4-31b: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 samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use samuelstolicny/claudie-expert-gemma4-31b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf samuelstolicny/claudie-expert-gemma4-31b: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 "samuelstolicny/claudie-expert-gemma4-31b: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"

Claudie Expert — Gemma 4 31B

Fine-tuned Gemma 4 31B-IT specialized on Claudie — an open-source platform for managing multi-cloud and hybrid-cloud Kubernetes infrastructure.

About Claudie

Claudie provisions and manages Kubernetes clusters declaratively across AWS, Azure, GCP, OCI, Hetzner, Exoscale, CloudRift, and OpenStack via the InputManifest CRD. Built by Berops.

Project: github.com/berops/claudie
Documentation: docs.claudie.io/latest

What this model knows

This model was fine-tuned on ~8,000 Claudie-specific Q&A conversations covering:

Claudie's 8 microservices (Manager, Terraformer, Ansibler, Kube-Eleven, Kuber, Claudie-Operator, Autoscaler-Adapter)
InputManifest CRD authoring for multi-cloud / GPU / autoscaling clusters
Debugging stuck states, NATS consumer lag, Terraform state locks, WireGuard issues
gRPC service communication, state machine, reconciliation loops
Claudie architecture, data flow between services
Kubernetes integration patterns

Files in this repo

File	Purpose
`model-*.safetensors`	Merged bf16 weights (for vLLM, Transformers)
`*.Q4_K_M.gguf`	4-bit GGUF (for Ollama, llama.cpp)
`chat_template.jinja`	Gemma 4 chat template

Usage

vLLM

vllm serve samuelstolicny/claudie-expert-gemma4-31b --max-model-len 8192

Ollama

ollama run hf.co/samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M

Transformers

from transformers import pipeline
pipe = pipeline("text-generation", model="samuelstolicny/claudie-expert-gemma4-31b")
print(pipe([{"role": "user", "content": "How do I add a GPU node pool in Hetzner?"}]))

Training

Base model: unsloth/gemma-4-31B-it
Method: LoRA bf16 (rank 64, alpha 128, all-linear)
Framework: Unsloth
Dataset: 8,012 synthetic Q&A conversations generated from the Claudie codebase + docs
Hardware: 1x RTX PRO 6000 96GB

License

Apache 2.0 — same as the base model and Claudie.

Downloads last month: 44

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for samuelstolicny/claudie-expert-gemma4-31b

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Finetuned

unsloth/gemma-4-31B-it

Quantized

(12)

this model