Instructions to use emperorofrome/gemma-4-E2B-it-GMCE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use emperorofrome/gemma-4-E2B-it-GMCE 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 emperorofrome/gemma-4-E2B-it-GMCE:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf emperorofrome/gemma-4-E2B-it-GMCE:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf emperorofrome/gemma-4-E2B-it-GMCE:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf emperorofrome/gemma-4-E2B-it-GMCE: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 emperorofrome/gemma-4-E2B-it-GMCE:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf emperorofrome/gemma-4-E2B-it-GMCE: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 emperorofrome/gemma-4-E2B-it-GMCE:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf emperorofrome/gemma-4-E2B-it-GMCE:Q4_K_M

Use Docker

docker model run hf.co/emperorofrome/gemma-4-E2B-it-GMCE:Q4_K_M

LM Studio
Jan
Ollama
How to use emperorofrome/gemma-4-E2B-it-GMCE with Ollama:
```
ollama run hf.co/emperorofrome/gemma-4-E2B-it-GMCE:Q4_K_M
```
Unsloth Desktop

How to use emperorofrome/gemma-4-E2B-it-GMCE with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf emperorofrome/gemma-4-E2B-it-GMCE: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": "emperorofrome/gemma-4-E2B-it-GMCE:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use emperorofrome/gemma-4-E2B-it-GMCE with Docker Model Runner:
```
docker model run hf.co/emperorofrome/gemma-4-E2B-it-GMCE:Q4_K_M
```

Lemonade

How to use emperorofrome/gemma-4-E2B-it-GMCE with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull emperorofrome/gemma-4-E2B-it-GMCE:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-E2B-it-GMCE-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use emperorofrome/gemma-4-E2B-it-GMCE with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf emperorofrome/gemma-4-E2B-it-GMCE: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 emperorofrome/gemma-4-E2B-it-GMCE:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use emperorofrome/gemma-4-E2B-it-GMCE with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf emperorofrome/gemma-4-E2B-it-GMCE: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 "emperorofrome/gemma-4-E2B-it-GMCE: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"

gemma-4-E2B-it-GMCE (GMCoder Efficiency)

google/gemma-4-E2B-it fine-tuned for GMCoder Efficiency, which makes answers shorter and more direct. Files: GGUF (Q8_0, Q6_K, Q5_K_M, Q4_K_M, BF16) and BF16 safetensors.

What it does (measured)

Our own unseen "Form B" exams, default chat mode, 60k token cap, single run per model, graded blind by one grader. Scores are approximate.

	Tokens (3 exams)	Ultimate (/25)	Historical (/100, approx)
gemma-4-E2B-it	20.4k	17	~58
gemma-4-E2B-it-GMCE	13.5k (-34%)	10	~50

Caveats

Less accurate than the base model in our tests: it is cheaper, but on the hardest exam it stopped after question 20 and scored lower. At this size the recipe costs accuracy. The larger gemma-4-E4B-it-GMCE holds accuracy much better.
Only the default mode was tested (our local server ignored Gemma's thinking switch).
Benchmarks are our own and small.