This repo offers quantized versions of google/gemma-3-4b-it for use with llama.cpp. Quantization was done using an unofficial Docker image and calibrated on 100 rows from the agentlans/LinguaNova dataset to maintain coherence and multilingual support. The importance matrix file is included.

Limitations

Optimized for multilingual natural language tasks.
May underperform on math, coding, and untested multimodal features.
Shares all limitations and biases of the original Gemma 3 models.

Notes

Ideal for resource-constrained environments.
Test on your data for best results.
See the original google/gemma-3-4b-it page for full details and guidelines.

This card covers only the quantized models.

agentlans/gemma-3-4b-it-GGUF

Gemma 3 4B Instruct Quantized Models

Limitations

Notes

agentlans/
gemma-3-4b-it-GGUF