None
None
Long Story Video Skill
Turn your idea into 10s–10min video—AI writes scripts, prompts, and generates footage automatically.
Ads Video Skill
Generate professional ads and sales videos—AI auto-generates scripts, prompts, and footage.
3D Science Explainer Video Skill
Convert scientific concepts into stunning 3D explain animations
Feedback
freeTrialImage.bannerPity
freeTrialImage.upgradeUnlock
- ✓freeTrialImage.benefitHd
- ✓freeTrialImage.benefitWatermark
- ✓freeTrialImage.benefitUnlimited
xiaomi ocr 0
Upload a scan and watch this 0.8B Xiaomi OCR 0 engine return tidy text, tables, math and handwriting — free, no signup, results in seconds.
All Tools
Discover our comprehensive AI-powered animation toolkit
MiniMax H3
MiniMax H3 AI Video Generator
Seedance 2.5
The Future of AI Video Is Here.
Seedance 2.0
The Future of AI Video Is Here.
Seedance 2.0
The Future of AI Video Is Here.
Gemini Omni
Gemini Omni Video Generator
Image to Video
Generate videos from images
Gemini Omni 1.2 Flash
AI Multi-Scene Shorts Generator
Create viral AI Shorts instantly
Why Xiaomi OCR 0 Fits Real Document Work
A single 0.8B checkpoint handles layout parsing, OCR-focused question answering and field capture, so you can retire several single-purpose tools instead of juggling them.
- One Checkpoint, Three JobsLayout parsing, OCR-driven question answering and key-field capture all run through the same compact model.
- Benchmark LeaderIt ranks first on Real5-OmniDocBench with 95.24 and takes second on OmniDocBench v1.6 and the Wild variant.
- Built for Messy InputsSkewed, warped, photographed and low-quality scans hold up as well as clean digital PDFs.
Run Xiaomi OCR 0 in Three Steps
From a page image to structured output in under a minute.
Xiaomi OCR 0 Capabilities at a Glance
Compact size, resilient parsing, handwriting coverage and open weights — where this 0.8B model earns its place.
Page Parsing That Adapts
Covers plain pages alongside scanned, warped, skewed and re-photographed documents.
Table and Equation Accuracy
Formula recognition scores 97.84 on UniMER-Test, with table structure at 92.27 on PubTabNet.
Handwriting and Calligraphy
Reaches 73 on Chronicles-OCR for mature scripts, matching Seed 2.0 Pro.
Document Question Answering
Averages 83.2 across five VQA suites, ahead of a 2B competitor at a fraction of the size.
Structured Field Capture
Returns organized fields from receipts and forms rather than a flat transcription.
Open Weights, Local Ready
Apache-2.0 weights ship with GGUF and BF16 builds for llama.cpp, Ollama and Transformers.
Xiaomi OCR 0: Your Questions Answered
What this compact OCR model does, how it scores and how to run it on your own hardware.
What exactly is Xiaomi OCR 0?
It is a 0.8B vision-language checkpoint tuned for document work — reading pages and answering OCR-related questions in a single pass.
How does it perform on benchmarks?
It leads Real5-OmniDocBench and lands second on both OmniDocBench v1.6 and Wild-OmniDocBench.
Does it handle handwritten text?
Yes — clerical, cursive, running and regular calligraphy are all supported, scoring 73 on Chronicles-OCR.
What went into its training?
Roughly 170M OCR-focused samples, Q-Mask text anchoring, continued pretraining and mixed-task reinforcement learning.
Can I self-host it?
Apache-2.0 weights are public, with community GGUF and BF16 conversions for llama.cpp, Ollama and Transformers.
Is transcription all it does?
No — it also answers questions about a page and turns key fields into structured output.
Put Xiaomi OCR 0 to Work on Your Files
Upload a page image and get parsed text, tables and structured fields back in seconds.