RepoAlerts
SponsorGet alerts

xiaomi-research/Xiaomi-OCR-0

Model

Get alerts like thisView on GitHubWebsiteShare on X

Can I trust it?

No red flags in our checks.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 3 days ago.

  • Licence OK

    Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

A unified 0.8B vision-language model for document parsing, OCR-centric understanding, key information extraction and visual question answering. It converts document pages to structured Markdown with HTML tables and LaTeX formulas, and includes an MCP service, an Agent Skill and…

Who it's for

Developers and document-processing teams building OCR, document parsing or document question-answering pipelines with local models

How to use it

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up xiaomi-research/Xiaomi-OCR-0 in my project. Follow its README: https://github.com/xiaomi-research/Xiaomi-OCR-0. Explain each step and check it is safe before running anything.

Read the README

Star curve

400From 0 to 400 stars between 28 Sept 2026 and 1 Nov 2026.

On the radar

1 Nov 2026: #94
Best place #94, on 1 Nov 2026. In the top 100 on 1 of the last 15 days.

Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.

Records

  • Best place on RepoAlerts: #94, on 1 Nov 2026

Get alerts for repos like this

We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.

23,610 GitHub repos watched and ranked every hour. Figures as of 1 November 2026.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![xiaomi-research/Xiaomi-OCR-0 on RepoAlerts](https://repoalerts.com/badge/xiaomi-research/Xiaomi-OCR-0.svg)](https://repoalerts.com/repo/xiaomi-research/Xiaomi-OCR-0?ref=badge)
Share on X
  • SoMarkAI/OXR

    An open-source document parsing model that converts PDFs and document images into Markdown or JSON with layout coordinates. It recognizes 13 element types, including tables, formulas and chemical stru

    ModelModels & inferencePython · 2,779 stars · +2,190 this week · 27 days old

  • OpenBMB/MiniCPM-OCR

    A family of OCR models for parsing Chinese and English documents and PDFs, including scans, photographs and curved pages. MiniCPM-OCR 1.0 (1.3B) recognizes text, tables, formulas and charts, and MiniC

    ModelModels & inferenceTypeScript · 724 stars · +724 this week · 5 days old

  • datalab-to/indra

    Indra OCR is a CPU-based OCR tool that converts PDFs and images into markdown, text, or JSON with line boxes, layout labels and reading order. It runs on ONNX Runtime without PyTorch or a GPU and supp

    CLI toolPython · 1,548 stars · +507 this week · 19 days old

  • ss062353-prog/on-device-vision-model

    A fully local, offline vision pipeline that pairs the SmolVLM-256M-Instruct vision-language model with RapidOCR multilingual OCR. It exposes an OpenAI-compatible API on localhost so text-only models c

    AppModels & inferencePython · 202 stars · +32 this week · 63 days old

  • op7418/guizang-tv

    A simplified Android home screen for Xiaomi TVs, showing a large-text app list, rotating wallpapers and shortcuts to HDMI inputs. Targets the MiTV-MTSU0 model; other Android TV devices are not the foc

    AppApps & desktopJava · 284 stars · +46 this week · 12 days old

  • YuriyLin/PaperRead

    A personal research workspace for reading academic papers in a Traditional Chinese interface. It combines topic and venue search over OpenAlex, DBLP and Crossref, a candidate list, a reading kanban, s

    Python · 324 stars · +10 this week · 22 days old