MiniCPM-OCR 1.0

Name: MiniCPM-OCR 1.0
Author: OpenBMB

OpenBMB · released 2026-10-21 · data checked 2026-11-06

MiniCPM-OCR 1.0 is a 1.3B-parameter OCR and document-parsing model from OpenBMB (CN), released 2026-10-21 under the Apache-2.0 license. It scores 82.7 on olmOCR-Bench (#10 of 24). It needs about 3.6 GB of memory at 16-bit.

Fine-tuned from MiniCPM-V 4.6. Chinese and English. Its OmniDocBench results are only in images. OpenBMB also released MiniCPM-OCR-Jev, which grades OCR output quality rather than doing OCR.

OmniDocBench v1.6

—

Not reported

olmOCR-Bench

82.7

#10 of 24 models

Parameters

1.3B

OCR specialist

Memory to run

~3.6 GB

16-bit weights plus about 1 GB

Benchmarks

olmOCR-Bench Lab-reported82.7

Best: OXR 1.0 87.8

The tick marks the best score on each benchmark. See how to read the ranking.

Specifications

Lab: OpenBMB (CN)
Type: OCR / document parsing specialist
Total parameters: 1.3B
License: Apache-2.0
Memory to run: ~3.6 GB at 16-bit
Released: 2026-10-21

Weights and usage on Hugging Face ↗

Closest alternatives

Falcon OCR 1.5 (270M, 82.4 on olmOCR-Bench, Apache-2.0)
olmOCR 2 (8.3B, 82.4 on olmOCR-Bench, Apache-2.0)
LightOnOCR-2 1B (1B, 83.2 on olmOCR-Bench, Apache-2.0)
jina-ocr-v1 (3.4B, 83.4 on olmOCR-Bench, CC-BY-NC-4.0)

Sources

https://huggingface.co/openbmb/MiniCPM-OCR-1.0

Something wrong here? Report it.