MiniCPM-OCR 1.0: 1.3B AI Model for Document Text Extraction and Understanding
The MiniCPM-OCR 1.0 model is a new 1.3-billion-parameter AI for optical character recognition, extracting text from documents, tables, and charts in English…
#science #AI #MachineLearning #OCR
The MiniCPM-OCR 1.0 model is a new 1.3-billion-parameter AI for optical character recognition, extracting text from documents, tables, and charts in English…
#science #AI #MachineLearning #OCR
MiniCPM-OCR 1.0: 1.3B AI Model for Document Text Extraction and Understanding
The MiniCPM-OCR 1.0 model is a new 1.3-billion-parameter AI for optical character recognition, extracting text from documents, tables, and charts in English…
sciherald.com
November 1, 2026 at 6:15 AM
MiniCPM-OCR 1.0: 1.3B AI Model for Document Text Extraction and Understanding
The MiniCPM-OCR 1.0 model is a new 1.3-billion-parameter AI for optical character recognition, extracting text from documents, tables, and charts in English…
#science #AI #MachineLearning #OCR
The MiniCPM-OCR 1.0 model is a new 1.3-billion-parameter AI for optical character recognition, extracting text from documents, tables, and charts in English…
#science #AI #MachineLearning #OCR
ModelBest ve OpenBMB, belge tanıma ve kalite kontrolü için geliştirdikleri MiniCPM-OCR model ailesini açık kaynaklı olarak yayımladı.
...
#MiniCPM #OpenSource #OCR #YapayZeka #LocalAI #YZ #AI
...
#MiniCPM #OpenSource #OCR #YapayZeka #LocalAI #YZ #AI
November 1, 2026 at 3:24 PM
ModelBest ve OpenBMB, belge tanıma ve kalite kontrolü için geliştirdikleri MiniCPM-OCR model ailesini açık kaynaklı olarak yayımladı.
...
#MiniCPM #OpenSource #OCR #YapayZeka #LocalAI #YZ #AI
...
#MiniCPM #OpenSource #OCR #YapayZeka #LocalAI #YZ #AI
ModelBest and OpenBMB Open-Source MiniCPM-OCR Series, Delivering High-Performance Document Parsing and AI-Powered Quality Control
BEIJING, Oct. 31, 2026 /PRNewswire/ -- ModelBest and OpenBMB jointly announced the release and open-source availability of the MiniCPM-OCR series, a family of models…
BEIJING, Oct. 31, 2026 /PRNewswire/ -- ModelBest and OpenBMB jointly announced the release and open-source availability of the MiniCPM-OCR series, a family of models…
ModelBest and OpenBMB Open-Source MiniCPM-OCR Series, Delivering High-Performance Document Parsing and AI-Powered Quality Control
BEIJING, Oct. 31, 2026 /PRNewswire/ -- ModelBest and OpenBMB jointly announced the release and open-source availability of the MiniCPM-OCR series, a family of models for efficient document parsing and parsing-quality assessment. The launch includes two models: MiniCPM-OCR 1.0 (1.3B) and MiniCPM-OCR Jev (2B). As the first OCR-focused model in the MiniCPM family, MiniCPM-OCR 1.0 brings top-tier parsing accuracy to a compact 1.3-billion-parameter architecture optimized for edge deployment, pushing forward the balance between efficiency and performance for open-source OCR models.
ohsem.me
October 31, 2026 at 5:32 PM
ModelBest and OpenBMB Open-Source MiniCPM-OCR Series, Delivering High-Performance Document Parsing and AI-Powered Quality Control
BEIJING, Oct. 31, 2026 /PRNewswire/ -- ModelBest and OpenBMB jointly announced the release and open-source availability of the MiniCPM-OCR series, a family of models…
BEIJING, Oct. 31, 2026 /PRNewswire/ -- ModelBest and OpenBMB jointly announced the release and open-source availability of the MiniCPM-OCR series, a family of models…
Posted NVFP4 GGUFs for Gemma-4-31B, MiniCPM-V-4.7-35B-A3B, Nanbeige4.3-33B. Built for 32GB VRAM or less. If it's worth it on consumer cards, I'll make the family. Ping me with suggestions.
https://www.esatapedico.com/posts/latest-model-uploads-gemma-minicpm-nanbeige/
#ai #inference #open-source
https://www.esatapedico.com/posts/latest-model-uploads-gemma-minicpm-nanbeige/
#ai #inference #open-source
November 3, 2026 at 12:10 AM
Posted NVFP4 GGUFs for Gemma-4-31B, MiniCPM-V-4.7-35B-A3B, Nanbeige4.3-33B. Built for 32GB VRAM or less. If it's worth it on consumer cards, I'll make the family. Ping me with suggestions.
https://www.esatapedico.com/posts/latest-model-uploads-gemma-minicpm-nanbeige/
#ai #inference #open-source
https://www.esatapedico.com/posts/latest-model-uploads-gemma-minicpm-nanbeige/
#ai #inference #open-source
MiniCPM OCR family 🔥 1st OCR from OpenBMB
✨ MiniCPM OCR 1.0
- 1.3B
- Apache 2.0
- 55% higher processing efficiency with DSpark
- Handles complex layouts, tables & formulas
✨ MiniCPM OCR 1.0
- 1.3B
- Apache 2.0
- 55% higher processing efficiency with DSpark
- Handles complex layouts, tables & formulas
October 27, 2026 at 6:06 PM
MiniCPM OCR family 🔥 1st OCR from OpenBMB
✨ MiniCPM OCR 1.0
- 1.3B
- Apache 2.0
- 55% higher processing efficiency with DSpark
- Handles complex layouts, tables & formulas
✨ MiniCPM OCR 1.0
- 1.3B
- Apache 2.0
- 55% higher processing efficiency with DSpark
- Handles complex layouts, tables & formulas
Introducing MiniCPM-OCR: High-Performance AI-Powered Document Parsing by ModelBest and OpenBMB#China#Beijing#AI_Quality_Control#ModelBest#MiniCPM-OCR
Introducing MiniCPM-OCR: High-Performance AI-Powered Document Parsing by ModelBest and OpenBMB
ModelBest and OpenBMB unveil the MiniCPM-OCR series, offering advanced document parsing solutions with AI-driven quality control for businesses.
third-news.com
October 31, 2026 at 3:47 PM
Introducing MiniCPM-OCR: High-Performance AI-Powered Document Parsing by ModelBest and OpenBMB#China#Beijing#AI_Quality_Control#ModelBest#MiniCPM-OCR
MiniCPM-OCR 1.0, 1,3 milyar parametreyle taranmış belgelerden, fotoğraflardan, tablolardan ve matematiksel formüllerden içerik çıkarabiliyor.
İkinci model MiniCPM-OCR Jev ise 2 milyar parametre kullanarak OCR sonuçlarını kaynak görüntülerle karşılaştırıyor ve olası tanıma hatalarını belirliyor.
...
İkinci model MiniCPM-OCR Jev ise 2 milyar parametre kullanarak OCR sonuçlarını kaynak görüntülerle karşılaştırıyor ve olası tanıma hatalarını belirliyor.
...
November 1, 2026 at 3:24 PM
MiniCPM-OCR 1.0, 1,3 milyar parametreyle taranmış belgelerden, fotoğraflardan, tablolardan ve matematiksel formüllerden içerik çıkarabiliyor.
İkinci model MiniCPM-OCR Jev ise 2 milyar parametre kullanarak OCR sonuçlarını kaynak görüntülerle karşılaştırıyor ve olası tanıma hatalarını belirliyor.
...
İkinci model MiniCPM-OCR Jev ise 2 milyar parametre kullanarak OCR sonuçlarını kaynak görüntülerle karşılaştırıyor ve olası tanıma hatalarını belirliyor.
...
🌐OpenBMB – Resmî GitHub deposu ve model dosyaları:
github.com/OpenBMB/Mini...
github.com/OpenBMB/Mini...
GitHub - OpenBMB/MiniCPM-OCR: Fast, accurate OCR with correctness assessment.
Fast, accurate OCR with correctness assessment. Contribute to OpenBMB/MiniCPM-OCR development by creating an account on GitHub.
github.com
November 1, 2026 at 3:24 PM
🌐OpenBMB – Resmî GitHub deposu ve model dosyaları:
github.com/OpenBMB/Mini...
github.com/OpenBMB/Mini...
hmm. prompt caching for minicpm seems broken under llama-server :/
October 30, 2026 at 11:02 AM
hmm. prompt caching for minicpm seems broken under llama-server :/
✨ MiniCPM OCR Jev
- 2B
- Apache 2.0
- Evaluates OCR accuracy, even from other models
- 0.936 AUROC on JevOCRBench
- Helps flag errors for human review
huggingface.co/collections/...
- 2B
- Apache 2.0
- Evaluates OCR accuracy, even from other models
- 0.936 AUROC on JevOCRBench
- Helps flag errors for human review
huggingface.co/collections/...
MiniCPM-OCR - a openbmb Collection
Fast parsing. High accuracy.
huggingface.co
October 27, 2026 at 6:06 PM
✨ MiniCPM OCR Jev
- 2B
- Apache 2.0
- Evaluates OCR accuracy, even from other models
- 0.936 AUROC on JevOCRBench
- Helps flag errors for human review
huggingface.co/collections/...
- 2B
- Apache 2.0
- Evaluates OCR accuracy, even from other models
- 0.936 AUROC on JevOCRBench
- Helps flag errors for human review
huggingface.co/collections/...
minicpm 35a3b's first try on my "solar skies" benchmark. many issues but it does work
October 30, 2026 at 10:39 AM
minicpm 35a3b's first try on my "solar skies" benchmark. many issues but it does work
(not fast but they intend to use it to train smaller)
MiniCPM-V also looking good too. Just lots of incredible medium models.
huggingface.co/openbmb/Mini...
MiniCPM-V also looking good too. Just lots of incredible medium models.
huggingface.co/openbmb/Mini...
openbmb/MiniCPM-V-4.7-35B-A3B · Hugging Face
Image-Text-to-Text model with 35B parameters. Download, explore files and run it on Hugging Face.
huggingface.co
October 31, 2026 at 2:10 AM
(not fast but they intend to use it to train smaller)
MiniCPM-V also looking good too. Just lots of incredible medium models.
huggingface.co/openbmb/Mini...
MiniCPM-V also looking good too. Just lots of incredible medium models.
huggingface.co/openbmb/Mini...
OpenBMB released MiniCPM-OCR 1.0, a 1.3B open-source model that turns scans, photos and PDFs into clean text, tables and formulas 📄 It comes with Jev, a 2B model that flags OCR results worth a second look. Apache 2.0, and it runs on vLLM, llama.cpp and Ollama.
#AI #OpenSource #OCR
#AI #OpenSource #OCR
openbmb/MiniCPM-OCR-1.0 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
October 28, 2026 at 1:25 AM
OpenBMB released MiniCPM-OCR 1.0, a 1.3B open-source model that turns scans, photos and PDFs into clean text, tables and formulas 📄 It comes with Jev, a 2B model that flags OCR results worth a second look. Apache 2.0, and it runs on vLLM, llama.cpp and Ollama.
#AI #OpenSource #OCR
#AI #OpenSource #OCR
by comparison minicpm-v-4.7-35a3b thinks for a couple seconds and then just starts writing code
October 30, 2026 at 10:22 AM
by comparison minicpm-v-4.7-35a3b thinks for a couple seconds and then just starts writing code
PolyStrata 在我的硬體配置，跑同樣的模型，同樣的脈絡長度，同樣的模型參數，比 llama.cpp 快1.5~2倍
https://github.com/VecSzn/PolyStrata
https://github.com/VecSzn/PolyStrata
GitHub - VecSzn/PolyStrata: Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.
Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engin...
github.com
November 2, 2026 at 7:49 AM
PolyStrata 在我的硬體配置，跑同樣的模型，同樣的脈絡長度，同樣的模型參數，比 llama.cpp 快1.5~2倍
https://github.com/VecSzn/PolyStrata
https://github.com/VecSzn/PolyStrata
openbmb/MiniCPM-OCR-1.0
A image text to text model from openbmb with 190 likes and 791 downloads on Hugging Face.
https://huggingface.co/openbmb/MiniCPM-OCR-1.0
via https://dailymd.cowerx.dev/
A image text to text model from openbmb with 190 likes and 791 downloads on Hugging Face.
https://huggingface.co/openbmb/MiniCPM-OCR-1.0
via https://dailymd.cowerx.dev/
openbmb/MiniCPM-OCR-1.0
A image text to text model from openbmb with 190 likes and 791 downloads on Hugging Face.
huggingface.co
October 28, 2026 at 1:02 PM
openbmb/MiniCPM-OCR-1.0
A image text to text model from openbmb with 190 likes and 791 downloads on Hugging Face.
https://huggingface.co/openbmb/MiniCPM-OCR-1.0
via https://dailymd.cowerx.dev/
A image text to text model from openbmb with 190 likes and 791 downloads on Hugging Face.
https://huggingface.co/openbmb/MiniCPM-OCR-1.0
via https://dailymd.cowerx.dev/
MiniCPM's dense-document OCR at small size was promising, so a dedicated OCR-1.0 makes sense. But no model card, no parameter count, no benchmark — hard to recommend this over PaddleOCR in production until weights and evals land.
OpenBMB Lists MiniCPM-OCR-1.0 and DSpark Variant on Model Hubs
OpenBMB has published model pages for MiniCPM-OCR-1.0 and MiniCPM-OCR-1.0-DSpark on Hugging Face, ModelScope and Modelers. The Hugging Face listing for the DSpark variant gives its task as image-text-to-text.
aichina.news
October 29, 2026 at 2:34 PM
MiniCPM's dense-document OCR at small size was promising, so a dedicated OCR-1.0 makes sense. But no model card, no parameter count, no benchmark — hard to recommend this over PaddleOCR in production until weights and evals land.
OPENBMB: MINICPM-OCR-1.0-DSPARK ON HUGGING FACE, 55% FASTER DECODING, 296M PARAMS
October 27, 2026 at 6:15 PM
OPENBMB: MINICPM-OCR-1.0-DSPARK ON HUGGING FACE, 55% FASTER DECODING, 296M PARAMS
OpenBMB just open-sourced a 1.3B OCR model (Apache 2.0) that runs on your own hardware.
AWS Textract charges $15-$50 per 1,000 pages for tables and forms. This is $0.
Tried swapping your OCR stack for it? https://flowtivity.ai/blog/minicpm-ocr-1-0-jev-local-document-parser/
#AI #OpenSource
AWS Textract charges $15-$50 per 1,000 pages for tables and forms. This is $0.
Tried swapping your OCR stack for it? https://flowtivity.ai/blog/minicpm-ocr-1-0-jev-local-document-parser/
#AI #OpenSource
November 1, 2026 at 9:38 AM
OpenBMB just open-sourced a 1.3B OCR model (Apache 2.0) that runs on your own hardware.
AWS Textract charges $15-$50 per 1,000 pages for tables and forms. This is $0.
Tried swapping your OCR stack for it? https://flowtivity.ai/blog/minicpm-ocr-1-0-jev-local-document-parser/
#AI #OpenSource
AWS Textract charges $15-$50 per 1,000 pages for tables and forms. This is $0.
Tried swapping your OCR stack for it? https://flowtivity.ai/blog/minicpm-ocr-1-0-jev-local-document-parser/
#AI #OpenSource
⚡ Ein neues multimodales Modell für Text und Bild.
🛠️ MiniCPM-OCR-1.0 von openbmb verarbeitet Bild- und Textdaten direkt und sorgt für…
🚀 Entdecke diesen und weitere KI-Geheimtipps auf Underground AI.
👉 https://underground-ai.bolt.app/
#OpenSource #KuenstlicheIntelligenz
🛠️ MiniCPM-OCR-1.0 von openbmb verarbeitet Bild- und Textdaten direkt und sorgt für…
🚀 Entdecke diesen und weitere KI-Geheimtipps auf Underground AI.
👉 https://underground-ai.bolt.app/
#OpenSource #KuenstlicheIntelligenz
October 28, 2026 at 4:03 PM
⚡ Ein neues multimodales Modell für Text und Bild.
🛠️ MiniCPM-OCR-1.0 von openbmb verarbeitet Bild- und Textdaten direkt und sorgt für…
🚀 Entdecke diesen und weitere KI-Geheimtipps auf Underground AI.
👉 https://underground-ai.bolt.app/
#OpenSource #KuenstlicheIntelligenz
🛠️ MiniCPM-OCR-1.0 von openbmb verarbeitet Bild- und Textdaten direkt und sorgt für…
🚀 Entdecke diesen und weitere KI-Geheimtipps auf Underground AI.
👉 https://underground-ai.bolt.app/
#OpenSource #KuenstlicheIntelligenz
圧縮文明：1B級SOTAが書き換える知能の地政学 #LLM #MiniCPM #AI蒸留 #1B級SOTA #地政学AI #圧縮文明 #2021OpenBMBのMiniCPM_令和AI史ざっくり解説 #五31 dopingconsomme.blogspot.com/2026/05/comp...
圧縮文明：1B級SOTAが書き換える知能の地政学 #LLM #MiniCPM #AI蒸留 #1B級SOTA #地政学AI #圧縮文明 #2021OpenBMBのMiniCPM_令和AI史ざっくり解説 #五31
doping consomme blog
dopingconsomme.blogspot.com
October 29, 2026 at 11:36 AM
圧縮文明：1B級SOTAが書き換える知能の地政学 #LLM #MiniCPM #AI蒸留 #1B級SOTA #地政学AI #圧縮文明 #2021OpenBMBのMiniCPM_令和AI史ざっくり解説 #五31 dopingconsomme.blogspot.com/2026/05/comp...
The source, dated, on The Deploy Log:
https://deployedbyai.com/log/14de670b93fa/minicpm-ocr-1-0-dspark/?k=br
https://deployedbyai.com/log/14de670b93fa/minicpm-ocr-1-0-dspark/?k=br
October 27, 2026 at 6:15 PM
The source, dated, on The Deploy Log:
https://deployedbyai.com/log/14de670b93fa/minicpm-ocr-1-0-dspark/?k=br
https://deployedbyai.com/log/14de670b93fa/minicpm-ocr-1-0-dspark/?k=br