Datalab's Indra OCR: a 1M-parameter open model that hits 44 pages/s on CPU across 80+ languages
VikParuchuri · x · 2026-10-23
Datalab detailed Indra OCR, the 1M-parameter model behind its $0.50/1k-page lite mode: pure CPU inference via ONNX (no PyTorch, no GPU), 44 pages/s on 32 cores (15x Tesseract, 10x PaddleOCR PP-OCR), scoring 66.7 on OmniParseBench vs 58.4 for PaddleOCR's PP-StructureV3, and covering 80+ languages, handwriting, tilted scans, and digital PDF text layers. Weights are open under openrail; Datalab's larger balanced/accurate modes score 91.6 and 93.5.
More from Models
- OpenAI blocks manual reset with 13% usage left: 'no reset needed right now' — AccomplishedSugar490 · 2026-10-23
- Meta's 816B Muse Spark Open scores 39, losing to 180B Qwen3.8-Flash-Next at 40 — BTA_Labs · 2026-10-23
- Gemini refuses to generate image in Docs, blames document size limit — viksit · 2026-10-23
- Dev jokes his true calling is telling everyone to try the latest DeepSeek — intellectronica · 2026-10-23
- SubQ Snap 1.1 ties for first on Artificial Analysis Decision Index with 384K context — ArtificialAnlys · 2026-10-23
- PolyAI unveils Dialog-RSN-1: audio-native voice model answering in under 300ms — matthen2 · 2026-10-23