Google Gemma 3B GGUF Quantized Open-Source Model - Supports Local Inference and Text Generation Tasks

Gemma 3 12b It Q5 K S GGUF

Developed by NikolayKozloff

This is the GGUF quantized version of Google Gemma 3B model, suitable for local inference and supports text generation tasks.

Large Language Model #Efficient Inference Optimization #Lightweight Deployment #Multi-turn Dialogue Support

Downloads 16

Release Time : 3/12/2025

Model Overview

A GGUF format version converted from Google Gemma 3B model, primarily used for text generation tasks and can run efficiently in local environments.

Model Features

Local Efficient Inference

Optimized through GGUF format for efficient operation on consumer-grade hardware

Quantized Version

Uses Q5_K_S quantization level to balance model size and inference quality

Easy Deployment

Can be easily deployed via llama.cpp without complex environment configuration

Model Capabilities

Text Generation

Dialogue Systems

Question Answering

Content Creation

Use Cases

Content Generation

Creative Writing

Generate creative content such as stories and poems

Can produce coherent and creative text

Dialogue Systems

Smart Assistant

Build locally-run conversational assistants

Can achieve smooth conversational interactions

🚀 NikolayKozloff/gemma-3-12b-it-Q5_K_S-GGUF

This model is converted to GGUF format and offers a convenient way to utilize the power of the original model in a specific format.

🚀 Quick Start

This model was converted to GGUF format from google/gemma-3-12b-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

Use with llama.cpp

CLI:

llama-cli --hf-repo NikolayKozloff/gemma-3-12b-it-Q5_K_S-GGUF --hf-file gemma-3-12b-it-q5_k_s.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo NikolayKozloff/gemma-3-12b-it-Q5_K_S-GGUF --hf-file gemma-3-12b-it-q5_k_s.gguf -c 2048

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 NikolayKozloff/gemma-3-12b-it-Q5_K_S-GGUF --hf-file gemma-3-12b-it-q5_k_s.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo NikolayKozloff/gemma-3-12b-it-Q5_K_S-GGUF --hf-file gemma-3-12b-it-q5_k_s.gguf -c 2048

📄 License

The license for this model is gemma.

Additional Information

Property	Details
Base Model	google/gemma-3-12b-it
Library Name	transformers
Pipeline Tag	image-text-to-text
Tags	llama-cpp, gguf-my-repo

⚠️ 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 "Acknowledge license" button to review and agree to the license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご