OpenBMB releases open-source MiniCPM-OCR family: 1.3B/2B models under Apache 2.0
AdinaYakup · x · 2026-10-28
OpenBMB has launched the MiniCPM-OCR collection on Hugging Face:
- MiniCPM-OCR 1.0: a 1.3B-parameter model under Apache 2.0, handling complex layouts, tables and formulas, with 55% higher processing efficiency via DSpark; 0.3B DSpark variant plus GGUF/AWQ/GPTQ quantizations available.
- MiniCPM-OCR Jev: a 2B-parameter Apache 2.0 model that evaluates OCR accuracy even from other models, scoring 0.936 AUROC on JevOCRBench and flagging errors for human review.
The full collection is downloadable as a Hugging Face Collection, targeting fast parsing and high accuracy.
Related event: OpenBMB Open-Sources MiniCPM-OCR Family with 1.3B SOTA Model(6 posts)→
More from Models
- Open-weight models now hold 72% of OpenRouter tokens as Tim Shi bets enterprises will own their intelligence — thursdai_pod · 2026-10-28
- Google launches Genie 4: its most realistic interactive world model with native audio and real-time steering — BorisMPower · 2026-10-28
- EmbeddingGemma 2 runs real-time embeddings on a MacBook CPU alone: 20ms text, 100ms images — generativist · 2026-10-28
- Google Gemma rounds up EmbeddingGemma 2 community projects, from WebGPU photo search to Apple Silicon — GlennCameronjr · 2026-10-28
- DeepSeek says "I'm ChatGPT" in identity test, resurfacing distillation allegations — ResonantFork · 2026-10-28
- Developer chats with a lamp fully locally using the new LFM3-Audio model — ngxson · 2026-10-28