MiniCPM-OCR 1.0 (1.3B) is the first OCR-specific model in the MiniCPM-V/o family. It focuses on text-centric document understanding — text, tables, formulas, charts, seals, and structured information extraction — and balances quality against speed on real-world captures.
Alternatives to MiniCPM-OCR-1.0
120 open-weight models that do the same job as MiniCPM-OCR-1.0 (1.3B OCR), ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.
Compare MiniCPM-OCR-1.0 with the top 3GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. It introduces Multi-Token Prediction (MTP) loss and stable full-task reinforcement learning to improve training efficiency, recognition accuracy, and generalization.
1.3B128K ctx MIT1.9M 2.2KJan 2026- Same category
- Similar size (1.3B vs 1.3B)
- Commercial use OK
- Widely used
📦 Model layout. This repository hosts HunyuanOCR-1.5 checkpoint at the root (target base weights). The DFlash speculative-decoding draft lives under dflash/, and the previous HunyuanOCR-1.0 is archived under v1.0/ (load it with subfolder="v1.0", or download the v1.0/ directory directly).
1.1B128K ctx Tencent Hunyuan Community License614.4K 849Nov 2025- Same category
- Similar size (1.1B vs 1.3B)
OvisOCR3 is a unified 0.8B multimodal model for OCR and document understanding. It integrates document parsing, general OCR, key information extraction, document figure captioning, and cross-page table reconstruction into a single compact model.
853M256K ctx Apache 2.0406.6K 128Oct 2026- Same category
- Similar size (853M vs 1.3B)
- Commercial use OK
Best OCR model . LightOnOCR-2-1B is LightOn's flagship OCR model, refined with RLVR training for maximum accuracy. We recommend this variant for most OCR tasks.
1B16K ctx Apache 2.0699.7K 852Jan 2026- Same category
- Similar size (1B vs 1.3B)
- Commercial use OK
TeleOCR is a lightweight (~1.2B parameters), open-source Vision-Language Model designed specifically for document parsing.
1.4B125K ctx Apache 2.018.2K 1.3KAug 2026- Same category
- Similar size (1.4B vs 1.3B)
- Commercial use OK
MinerU2.5-Pro is our latest document parsing model (PDF-to-Markdown) that establishes a new industry standard. By focusing entirely on data engineering without altering the original 1.2B-parameter architecture, it delivers exceptional results across the board:
1.2B8K ctx Apache 2.034.9K 118May 2026- Same category
- Similar size (1.2B vs 1.3B)
- Commercial use OK
MinerU2.5-Pro is our latest document parsing model (PDF-to-Markdown) that establishes a new industry standard. By focusing entirely on data engineering without altering the original 1.2B-parameter architecture, it delivers exceptional results across the board:
1.2B8K ctx Apache 2.027.8K 185Apr 2026- Same category
- Similar size (1.2B vs 1.3B)
- Commercial use OK
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
959M128K ctx Apache 2.096.9K 595May 2026- Same category
- Similar size (959M vs 1.3B)
- Commercial use OK
MinerU2.5 is a 1.2B-parameter vision-language model for document parsing that achieves state-of-the-art accuracy with high computational efficiency.
1.2B16K ctx AGPL 3.077.7K 374Sept 2025- Same category
- Similar size (1.2B vs 1.3B)
- Commercial use OK
MiniCPM-OCR Jev (2B) is an OCR quality-assessment model for text, formula, and table regions. Given a region image and a candidate OCR result, it returns a score from 0 to 1 — higher means the candidate is more likely correct.
2.2B256K ctx Apache 2.075.8K 99Oct 2026- Same category
- Similar size (2.2B vs 1.3B)
- Commercial use OK
- Newer release
It works on a range of documents (see usage and benchmarks).
686M256K ctx OpenRAIL615.2K 147May 2026- Same category
- Similar size (686M vs 1.3B)
We also ship smaller models for line-level text detection and ocr error detection. It works on a range of documents (see usage and benchmarks).
689M256K ctx OpenRAIL136.1K 54Oct 2026- Same category
- Similar size (689M vs 1.3B)
- Newer release
Please refer to the official vLLM recipe for deployment details:
3.3BA1.1B32K ctx MIT5.6M 5KJun 2026- Same category
- Larger (3.3B vs 1.3B)
- Commercial use OK
- Widely used
Same architecture as LightOnOCR-2-1B, new capabilities. LightOnOCR-3-1B keeps the architecture of LightOn's previous LightOnOCR-2 models, so switching requires no change, and adds the new grounding, image description and chart extraction features.
1B16K ctx Apache 2.04.4K 33Oct 2026- Same category
- Similar size (1B vs 1.3B)
- Commercial use OK
Full BF16 version of the model. We recommend this variant for inference and further fine-tuning.
1.2B8K ctx Apache 2.014.4K 256Oct 2025- Same category
- Similar size (1.2B vs 1.3B)
- Commercial use OK
Smallest model. LightOnOCR-3-0.8B is the lightest model of LightOn's LightOnOCR-3 family, with the same layout and visual understanding features.
853M256K ctx Apache 2.015K 105Oct 2026- Same category
- Similar size (853M vs 1.3B)
- Commercial use OK
We are pleased to announce the release of OvisOCR2, a compact 0.8B end-to-end model for page-level document parsing. Given a document page image, OvisOCR2 generates a Markdown representation in natural reading order, covering text, formulas, tables, and visual regions.
853M256K ctx Apache 2.024.4K 504Jul 2026- Same category
- Similar size (853M vs 1.3B)
- Commercial use OK
PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
959M128K ctx Apache 2.016.3K 668Jan 2026- Same category
- Similar size (959M vs 1.3B)
- Commercial use OK
Sparse Reference Sliding Window Attention (SR-SWA): Compresses text-visual attention interactions from ultra-long sequences down to a fixed-size set of working references (e.g., 512 tokens).
3.3BA1.1B128K ctx MIT612.1K 717Oct 2026- Same category
- Larger (3.3B vs 1.3B)
- Commercial use OK
- Newer release
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
959M128K ctx Apache 2.018.8K 1.7KOct 2025- Same category
- Similar size (959M vs 1.3B)
- Commercial use OK
Base model for fine-tuning. This is the pre-RLVR checkpoint with strong OCR capabilities, ideal as a starting point for domain adaptation and custom fine-tuning.
1B16K ctx Apache 2.03.6K 14Jan 2026- Same category
- Similar size (1B vs 1.3B)
- Commercial use OK
Best model with image localization. This model predicts both text and precise bounding boxes for embedded images, refined with RLVR using IoU-based rewards for maximum localization accuracy.
1B16K ctx Apache 2.03K 30Jan 2026- Same category
- Similar size (1B vs 1.3B)
- Commercial use OK
Refer to 🌟GitHub for guidance on model inference acceleration and PDF processing, etc.
3.3BA1.1B8K ctx MIT1.8M 3.5KOct 2025- Same category
- Larger (3.3B vs 1.3B)
- Commercial use OK
- Widely used
Merged bbox variant (advanced). This model combines OCR-improving RLVR signals with bounding-box-focused RLVR updates via joint merging, preserving OCR quality while providing image localization.
1B16K ctx Apache 2.01.4K 18Jan 2026- Same category
- Similar size (1B vs 1.3B)
- Commercial use OK