Model reference · open weights

olmOCR-2-1025

olmOCR-2-1025 is an open-weight language model from allenai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

LLMs allenai 2 variants 277k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What olmOCR-2-1025 is

olmOCR-2-7B-1025-FP8 Quantized to FP8 Version of olmOCR-2-7B-1025, using llmcompressor. This is a release of the olmOCR model that's fine tuned from Qwen2.5-VL-7B-Instruct using the olmOCR-mix-1025 dataset. It has been additionally fine tuned using GRPO RL training to boost its performance at math equations, tables, and other tricky OCR cases. Quick links: - 📃 Paper - 🤗 SFT Dataset - 🤗 RL Dataset - 🛠️ Code - 🎮 Demo The best way to use this model is via the olmOCR toolkit. The toolkit comes with an efficient inference setup via VLLM that can handle millions of documents at scale. olmOCR-Bench Scores This model scores the following scores on olmOCR-bench when used with the olmOCR toolkit toolkit which automatically renders, rotates, and retries pages as needed. Usage This model expects as input a single document image, rendered such that the longest dimension is 1288 pixels. The prompt must then contain the additional metadata from the document, and the easiest way to generate this is to use the methods provided by the olmOCR toolkit. Manual Prompting If you want to prompt this model manually instead of using the olmOCR toolkit, please see the code below. In normal usage, the olmOCR toolkit builds the prompt by rendering the PDF page, and extracting relevant text blocks and image metadata. To duplicate that you will need to and then run the following sample code. License and use This model is licensed under Apache 2.0. It is intended for research and educational use in accordance with Ai2's Responsible Use Guidelines.

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

Specifications

What it is

Makerallenai
TypeLanguage models
Parameters (lead)8.3B
Context125k tokens
Variants2
Runs withtransformers
Based onQwen/Qwen2.5-VL-7B-Instruct
Released2025-10-06
Popularity277k downloads / month
Likes254
LicenceOpen weights

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.

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.

VariantParamsPrecisionVRAMFits 16 GBWeights
olmOCR-2-7B-1025-FP88.3BFP8~9.5 GBWeights ↗
olmOCR-2-7B-10258.3BBF16~19.1 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys olmocr-2-1025 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (olmocr-2-1025 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":"olmocr-2-1025","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Languages

en

Tags

transformers safetensors qwen2_5_vl image-text-to-text conversational en eval-results text-generation-inference endpoints_compatible compressed-tensors deploy:azure

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want olmOCR-2-1025 on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More language models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms