---
license: apache-2.0
tags: [gguf, document-understanding, chart-qa, pix2struct, image-to-text]
pipeline_tag: image-to-text
---
# Pix2Struct Base (GGUF)

Variable-resolution image-to-text model for documents, charts, tables.
282M params (12L encoder + 12L decoder), Apache-2.0.

Encoder parity: cos=1.000000 vs HuggingFace.
Source: [google/pix2struct-base](https://huggingface.co/google/pix2struct-base).