Gemma 3 4b It Q4 K M GGUF

🚀 Aldaris/gemma-3-4b-it-Q4_K_M-GGUF

This project provides a GGUF - formatted conversion of the google/gemma-3-4b-it model, enabling seamless integration with llama.cpp.

🚀 Quick Start

This model was converted to GGUF format from google/gemma-3-4b-it using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

📦 Installation

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

💻 Usage Examples

Basic Usage

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Aldaris/gemma-3-4b-it-Q4_K_M-GGUF --hf-file gemma-3-4b-it-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Aldaris/gemma-3-4b-it-Q4_K_M-GGUF --hf-file gemma-3-4b-it-q4_k_m.gguf -c 2048

Advanced Usage

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL = 1 flag along with other hardware - specific flags (for ex: LLAMA_CUDA = 1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Aldaris/gemma-3-4b-it-Q4_K_M-GGUF --hf-file gemma-3-4b-it-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Aldaris/gemma-3-4b-it-Q4_K_M-GGUF --hf-file gemma-3-4b-it-q4_k_m.gguf -c 2048

📄 License

The model is under the gemma license.

📋 Information Table

⚠️ Important Note

To access Gemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging Face and click below. Requests are processed immediately.

💡 Usage Tip

You can click the following button to acknowledge the license: Acknowledge license