jc-builds/Gemma-3-4B-Q4_K_M-GGUF

Gemma-3-4B Q4_K_M GGUF

This is a Q4_K_M quantized GGUF conversion of google/gemma-3-4b-it optimized for on-device inference with llama.cpp.

Model Details

Property	Value
Original Model	Gemma 3 4B Instruct
Parameters	4 billion
Quantization	Q4_K_M (4-bit, medium quality)
File Size	~2.5 GB
Context Window	8,192 tokens
Architecture	Gemma 3

Intended Use

This model is optimized for:

• Mobile/Edge Deployment: Runs efficiently on iOS devices with 8GB+ RAM (iPhone 15 Pro, 16, etc.)
• llama.cpp Integration: Compatible with llama.cpp and its bindings
• On-Device AI: Private, offline inference without cloud dependencies

Capabilities

• General conversation and Q&A
• Code assistance
• Creative writing
• Reasoning and analysis
• Multilingual support

Usage with llama.cpp

./llama-cli -m Gemma-3-4B-Q4_K_M.gguf -p "Your prompt here" -n 512

License

This model is subject to Google's Gemma Terms of Use. Please review the license terms before use.

Attribution

• Original Model: Gemma 3 4B by Google
• Quantization: jc-builds