Gemma 3 27b It Q4 K M GGUF

🚀 paultimothymooney/gemma-3-27b-it-Q4_K_M-GGUF

This model is a conversion to the GGUF format from the original model google/gemma-3-27b-it. The conversion was carried out using llama.cpp via the ggml.ai's GGUF-my-repo space. For more in - depth details about the model, refer to the original model card.

⚠️ 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.

Button: Acknowledge license

🚀 Quick Start

✨ Features

• This model is a GGUF - formatted conversion of the original google/gemma-3-27b-it model, enabling compatibility with llama.cpp.

📦 Installation

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

brew install llama.cpp

💻 Usage Examples

Basic Usage

You can use this model with llama.cpp in both CLI and server modes.

CLI:

llama-cli --hf-repo paultimothymooney/gemma-3-27b-it-Q4_K_M-GGUF --hf-file gemma-3-27b-it-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo paultimothymooney/gemma-3-27b-it-Q4_K_M-GGUF --hf-file gemma-3-27b-it-q4_k_m.gguf -c 2048

Advanced Usage

You can also use this checkpoint directly following the usage steps in the Llama.cpp repo:

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 paultimothymooney/gemma-3-27b-it-Q4_K_M-GGUF --hf-file gemma-3-27b-it-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo paultimothymooney/gemma-3-27b-it-Q4_K_M-GGUF --hf-file gemma-3-27b-it-q4_k_m.gguf -c 2048

📄 License

The model uses the gemma license.