model: Granite4 Vision by gabe-l-hart · Pull Request #23545 · ggml-org/llama.cpp
Granite Vision 4.1 4B is a new vision-language model designed for efficient structured document extraction. It excels at tasks like chart, table, and key-value pair extraction, offering competitive performance in a compact 4B parameter size. This makes it a lightweight alternative to larger models for specialized document analysis. AI
IMPACT Provides a compact, efficient solution for specialized document analysis tasks like chart and table extraction.