Datalab Releases Indra OCR 1.1: 1M-Parameter Model Runs 44 Pages/sec on CPU
Datalab released Indra OCR 1.1, a 1M-parameter OCR model that processes 44 pages/sec on CPU with no GPU required; it scores 71.4 on OmniParseBench with the --math flag, beating Tencent's 1.1B HunyuanOCR and approaching DeepSeek OCR 2.
2026-10-20 ~ 2026-10-20 · 4 related posts
- Episode 1: Datalab Open-Sources Indra, a 1M-Parameter OCR Model Hitting 49 Pages/sec on CPU(2026-10-14, 6 posts)
- Episode 2: Indra: A 1M-Parameter Open OCR Model 15x Faster Than Tesseract(2026-10-16, 3 posts)
- Episode 3: Datalab Releases Indra OCR 1.1: 1M-Parameter Model Runs 44 Pages/sec on CPU(2026-10-20, 4 posts)
- Datalab ships Indra OCR 1.1: 1M-param model does 44 pages/s on CPU, near DeepSeek OCR 2 accuracy — VikParuchuri · 2026-10-20
- Indra OCR lands on Hugging Face: ONNX-based, CPU-only, 80+ languages with layout output — VikParuchuri · 2026-10-20
- With --math flag, 12M-param Indra OCR scores 71.4 on OmniParseBench, beating HunyuanOCR's 64.6 — VikParuchuri · 2026-10-20
- Indra OCR 1.1 improves language support, adds handwriting, fixes rotation and layout bugs — VikParuchuri · 2026-10-20