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

Notebooks
Google Colab
Kaggle
Local Apps Settings

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

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/cafkafk/gemma-4-E2B-it-GGUF-test:Q4_K_M

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

How to use cafkafk/gemma-4-E2B-it-GGUF-test with Pi:

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use cafkafk/gemma-4-E2B-it-GGUF-test with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cafkafk/gemma-4-E2B-it-GGUF-test:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-E2B-it-GGUF-test-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use cafkafk/gemma-4-E2B-it-GGUF-test with Hermes Agent:

Start the llama.cpp server

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

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use cafkafk/gemma-4-E2B-it-GGUF-test with OpenClaw:

Start the llama.cpp server

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

This is a test / learning quantization.

I made these GGUFs while learning how quantization works. They are not intended for production or serious use, and come with no quality guarantees.

For high-quality, well-maintained quants of this model, please use one of:

bartowski

mradermacher

This repository exists purely as a personal learning artifact.

Source model

Quantized from google/gemma-4-E2B-it.

Files

File	Quant type	Size
`gemma-4-E2B-it-Q8_0.gguf`	Q8_0	4.97 GB
`gemma-4-E2B-it-Q6_K.gguf`	Q6_K	3.85 GB
`gemma-4-E2B-it-Q5_K_M.gguf`	Q5_K_M	3.63 GB
`gemma-4-E2B-it-Q4_K_M.gguf`	Q4_K_M	3.43 GB
`gemma-4-E2B-it-IQ4_XS.gguf`	IQ4_XS	3.30 GB
`gemma-4-E2B-it-IQ3_M.gguf`	IQ3_M	3.13 GB

License

These files are derivative works of google/gemma-4-E2B-it and are distributed under the same terms.

Use of Gemma is governed by the Gemma Terms of Use.

By downloading or using these files you agree to the Gemma Terms of Use.

Downloads last month: 177

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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

Model tree for cafkafk/gemma-4-E2B-it-GGUF-test

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Quantized

(412)

this model