agentlans/Qwen3-4B-multilingual-sft-GGUF

Qwen 3 4B Multilingual Quantized Models

This repo contains quantized versions of the agentlans/Qwen3-4B-multilingual-sft model, optimized for efficient local use with llama.cpp.

The models were quantized using an unofficial Docker image and calibrated on the first 100 rows of the LinguaNova dataset to maintain strong multilingual performance.

These quantized models share the same strengths and limitations as the original Qwen 3 4B multilingual model. They offer a lighter, faster alternative for inference with minor trade-offs in precision.