granite-docling

About

What granite-docling is

granite-docling-258m Model Summary: Granite Docling 258M builds upon the Idefics3 architecture, but introduces two key modifications: it replaces the vision encoder with siglip2-base-patch16-512 and substitutes the language model with a Granite 165M LLM. Try out our Granite-Docling-258 demo today. - Developed by: IBM Research - Model type: Multi-modal model (image+text-to-text) - Language(s): English (NLP) - License: Apache 2.0 - Release Date: September 17, 2025 Granite-docling-258M is fully integrated into the Docling pipelines, carrying over existing features while introducing a number of powerful new features, including: - 🔢 Enhanced Equation Recognition: More accurate detection and formatting of mathematical formulas - 🧩 Flexible Inference Modes: Choose between full-page inference, bbox-guided region inference - 🧘 Improved Stability: Tends to avoid infinite loops more effectively - 🧮 Enhanced Inline Equations: Better inline math recognition - 🧾 Document Element QA: Answer questions about a document’s structure such as the presence and order of document elements - 🌍 Japanese, Arabic and Chinese support (experimental) Getting started The easiest way to use this model is through the 🐥Docling library. It will automatically download this model and convert documents to various formats for you. Install the latest version of docling through pip, then use the following CLI command: Alternatively, you can use bare transformers, vllm, onnx or mlx-vlm to perform inference, and docling-core APIs to convert results to variety of output formats (md, html, etc.): 💻 Local inference on Apple Silicon with MLX: see here ℹ️ If you see trouble running granite-docling with the codes above, check the troubleshooting section at the bottom ⬇️. Intended Use Granite-Docling is designed to complement the Docling library, not replace it. It integrates as a component within larger Docling library, consolidating the functions of multiple single-purpose models into a single, compact VLM. However, Granite-Docling is not intended for general image understanding. For tasks focused solely on image-text input, we recommend using Granite Vision models, which are purpose-built and optimized for im

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys granite-docling for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (granite-docling below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"granite-docling","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Papers

Licence

Open weights

Sources

Weights & code

Explore

More language models