ZRX1Raziel/gemma-3b-it

Gemma 3B IT GGUF

This is a GGUF (GPT-Generated Unified Format) version of the Gemma 3B Instruct model.

Usage

You can use this model with llama.cpp, Ollama, or other GGUF-compatible inference engines.

With llama.cpp:

./main -m gemma-3b-it.gguf -p "Your prompt here"

With Ollama:

ollama create gemma-3b-it -f Modelfile
ollama run gemma-3b-it

Model Details

• Base Model: Google Gemma 3B Instruct
• Format: GGUF
• File Size: 0.00 GB