Indra: a 1M-parameter OCR model that runs 49 pages/s on CPU, 11x faster than PaddleOCR
soldni · x · 2026-10-14
Vik Paruchuri introduced Indra, an OCR model with just 1M parameters:
- 49 pages/s on CPU — 11x faster than PaddleOCR and 17x faster than Tesseract
- Scores 41.3 on OmniParseBench text vs 35.8 (PaddleOCR) and 19.3 (Tesseract)
- Outputs full layout and line-level bounding boxes
A tiny model beating mature pipelines on both speed and accuracy — notable for anyone building document-processing workflows.
More from Models
- DeepSeek ships V4.1-Flash-1017: open weights, 1M context, claims Opus 5-level coding — CurieuxExplorer · 2026-10-17
- Elorian launches Glimpse, an Astra-level visual reasoning model at 17x lower cost — CurieuxExplorer · 2026-10-17
- Reflection AI open-sources Beam weights under Apache 2.0 with Mirror CLI harness — CurieuxExplorer · 2026-10-17
- Generative UI 101: Building Live Interfaces with Agents on Opus 5.5 and Rivals — EXM7777 · 2026-10-17
- OpenAI's new $500 tier and $200 plan throttling are driving power users away — cybrstg · 2026-10-17
- DeepSeek shows rapid vision gains: agent self-checks screenshots to build 3D scene — cedric_chee · 2026-10-17