Zoont/InternVL3-2B-4-Bit-GGUF-with-mmproj

GGUF Conversion & Quantization of OpenGVLab/InternVL3-2B (4-Bit Quantization)

This model is converted & quantized from OpenGVLab/InternVL3-2B using llama.cpp version 6217 (7a6e91ad)

All quants made using imatrix option with Bartowski's dataset

Model Details

For more details about the model, see its original model card