Indra: a 1M-parameter OCR model 15x faster than Tesseract on CPU
VictorSanh · x · 2026-10-17
Vik Paruchuri (Datalab founder) announced Indra, a tiny 1M-parameter OCR model that runs 15x faster than Tesseract on CPU while being significantly more accurate. He says he's still surprised by how good it is; the launch was amplified by Hugging Face's Victor Sanh. A CPU-friendly, ultra-light OCR model like this is compelling for local deployment and high-volume document processing.
Related event: Indra: A 1M-Parameter Open OCR Model 15x Faster Than Tesseract(3 posts)→
More from Models
- DeepSeek V4.1 Flash ships a two-stage refusal guardrail, uncensoring effort finds — cephaloform · 2026-10-20
- Meta releases Muse Glimmer, a 30B open-weight agentic model that runs on a single consumer GPU — AIatMeta · 2026-10-20
- Maxwell debuts as 'world's first Code Execution Model', early access open — tri_dao · 2026-10-20
- d1-ultra tops Artificial Analysis Decision Index by a wide margin — JosephJacks_ · 2026-10-20
- Deutsche Bank: Meta's Muse still leads ChatGPT in downloads and DAUs 36 days post-launch — alexandr_wang · 2026-10-20
- Uncensored DeepSeek V4.1 Flash FP8 finetune trends on Hugging Face — dealignai · 2026-10-20