Instructions to use Austriani/Gemma-4-E2B-it-ik_llama.cpp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Austriani/Gemma-4-E2B-it-ik_llama.cpp 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 Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16
# Run inference directly in the terminal:
llama cli -hf Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16
# Run inference directly in the terminal:
llama cli -hf Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16
# Run inference directly in the terminal:
./build/bin/llama cli -hf Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16

Use Docker

docker model run hf.co/Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16

Llama new
LM Studio
Jan
Ollama
How to use Austriani/Gemma-4-E2B-it-ik_llama.cpp with Ollama:
```
ollama run hf.co/Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16
```
Unsloth Desktop

How to use Austriani/Gemma-4-E2B-it-ik_llama.cpp with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16

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": "Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Austriani/Gemma-4-E2B-it-ik_llama.cpp with Docker Model Runner:
```
docker model run hf.co/Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16
```

Lemonade

How to use Austriani/Gemma-4-E2B-it-ik_llama.cpp with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16

Run and chat with the model

lemonade run user.Gemma-4-E2B-it-ik_llama.cpp-BF16

List all available models

lemonade list

Hermes Agent

How to use Austriani/Gemma-4-E2B-it-ik_llama.cpp with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16

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 Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Austriani/Gemma-4-E2B-it-ik_llama.cpp with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16

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 "Austriani/Gemma-4-E2B-it-ik_llama.cpp:BF16" \
  --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"

Heeey :>, just made a quant to test on my CPU, uploading it there cuz why not?

It should be okay, speeds are ~16% slower (inference) and ~5% slower (prompt processing), but also -17% memory footprint over Q4_K_M. Its only on my CPU of Intel Core Ultra 7 265K, I don't have any dedicated GPU, so with GPU it will be probably faster than Q4_K_M.

Downloads last month: 651

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

16-bit

Inference Providers NEW

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

Model tree for Austriani/Gemma-4-E2B-it-ik_llama.cpp

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Quantized

(444)

this model

Austriani
/

Gemma-4-E2B-it-ik_llama.cpp

Model tree for Austriani/Gemma-4-E2B-it-ik_llama.cpp

Dataset used to train Austriani/Gemma-4-E2B-it-ik_llama.cpp