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
Xiaomi OCR 0 is a tiny 0.8B vision-language model that reads scanned pages, tables, equations and handwriting, returning tidy structured text.
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.
Veo3.1
Create Stunning Videos with Veo3.1
FLUX 3 Video Generator
Kling 3.0
Next-Gen AI Video Generator
Grok Video Generator
Create Videos from Text or Images with AI
MiniMax H3 video generator
MiniMax H3 AI Video Generator
What Xiaomi OCR 0 Brings to Your Documents
A single 0.8B checkpoint handles page parsing, OCR-focused visual Q&A and field extraction, replacing several narrow utilities with one lightweight download.
- One Model, Three JobsPage parsing, OCR-driven visual Q&A and field extraction all run from the same small checkpoint.
- Benchmark LeaderScores 95.24 to lead Real5-OmniDocBench, and lands second on both OmniDocBench v1.6 and Wild-OmniDocBench.
- Built for Messy ScansWarped, skewed and phone-captured pages are handled as reliably as pristine digital PDFs.
Run Xiaomi OCR 0 in Three Steps
From a raw page image to tidy structured text in a few clicks.
What Xiaomi OCR 0 Can Do
Light on resources yet strong on hard pages: handwriting support, open weights and dependable parsing across the tasks that matter.
Page Parsing
Covers everyday pages along with scans, warped sheets, skewed angles and re-photographed documents.
Tables and Formulas
Reaches 97.84 on UniMER-Test for formulas and 92.27 on PubTabNet for table structure.
Handwriting and Calligraphy
Earns 73 on Chronicles-OCR for mature scripts, matching Seed 2.0 Pro.
Document Q&A
Averages 83.2 across five visual question answering suites, beating a 2B competitor at a fraction of the size.
Structured Fields
Returns key-value fields from receipts and forms rather than a flat transcription.
Open Weights, Local Runs
Apache-2.0 weights ship with GGUF and BF16 builds for llama.cpp, Ollama and Transformers.
Xiaomi OCR 0: Common Questions
Answers on what this small OCR model does, how it scores and how to run it yourself.
What exactly is Xiaomi OCR 0?
It is a compact 0.8B vision-language model tuned for reading documents, so transcription and OCR-related questions are handled in one pass.
Where does it rank on benchmarks?
It leads Real5-OmniDocBench and takes second place on OmniDocBench v1.6 and Wild-OmniDocBench.
Does it handle handwriting?
Yes — clerical, cursive, running and regular calligraphic scripts are all supported, scoring 73 on Chronicles-OCR.
What does its training recipe look like?
Roughly 170M OCR-focused samples, Q-Mask text anchoring, continued pretraining and mixed-task reinforcement learning.
Is local deployment possible?
Apache-2.0 weights are available, and the community provides 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 Pages
Upload one page image and get back parsed text, tables and structured fields within seconds — no setup required.