4 items
Перевод манги в браузере через локальные LLM (Qwen / Ollama / LM Studio). Manga Translate LLM is an open-source manga translation system that runs entirely on your own computer. It combines a Chrome extension (side panel interface), a FastAPI backend (Docker-containerized), and local language models via LM Studio or Ollama — no cloud services, no API keys, your images never leave your machine. Built for weak, local models Unlike tools that need a big cloud model or high-end GPU, this extension is engineered to work well on modest local models (9B+ parameters). Instead of asking a small model to translate an entire page in one shot — which small models handle poorly — the pipeline breaks translation into structured stages: OCR — reads the raw text on the page Whole-page vision analysis — a vision model reviews the image, fixes/groups OCR results, and does a first translation pass Panel-specific re-reading — a focused vision pass re-reads each panel at full resolution Voting — cheap requests run in parallel, majority answer wins, catching one-off mistakes Have a powerful local model or a paid API instead? Turbo mode collapses the pipeline to the minimum number of requests, translating up to 10× faster by skipping the extra scaffolding. Features Fully local processing — your manga images and translations never leave your PC Works with LM Studio or Ollama as the LLM backend Simple mode for everyday use, Developer mode with debugging tools, pipeline toggles, and direct LLM chat Ready-made hardware presets for different VRAM configurations UI available in 13 languages: English, Russian, German, French, Spanish, Portuguese, Italian, Polish, Japanese, Korean, Chinese, Arabic, Turkish Requirements Docker must be installed, along with local language models (LM Studio recommended for better performance on lower-VRAM machines). Full step-by-step installation instructions and documentation are available on GitHub. Installation & documentation (choose your language) 🇬🇧 English: https://github.com/mega-chizi/MangaTranslateLLM/tree/main/README/en 🇷🇺 Установка на русском: https://github.com/mega-chizi/MangaTranslateLLM/tree/main/README/ru 🇩🇪 Installation auf Deutsch: https://github.com/mega-chizi/MangaTranslateLLM/tree/main/README/de 🇫🇷 Installation en français: https://github.com/mega-chizi/MangaTranslateLLM/tree/main/README/fr 🇪🇸 Instalación en español: https://github.com/mega-chizi/MangaTranslateLLM/tree/main/README/es 🇵🇹 Instalação em português: https://github.com/mega-chizi/MangaTranslateLLM/tree/main/README/pt 🇮🇹 Installazione in italiano: https://github.com/mega-chizi/MangaTranslateLLM/tree/main/README/it 🇵🇱 Instalacja po polsku: https://github.com/mega-chizi/MangaTranslateLLM/tree/main/README/pl 🇯🇵 日本語でのインストール: https://github.com/mega-chizi/MangaTranslateLLM/tree/main/README/ja 🇰🇷 한국어 설치 안내: https://github.com/mega-chizi/MangaTranslateLLM/tree/main/README/ko 🇨🇳 中文安装说明: https://github.com/mega-chizi/MangaTranslateLLM/tree/main/README/zh 🇸🇦 التثبيت بالعربية: https://github.com/mega-chizi/MangaTranslateLLM/tree/main/README/ar 🇹🇷 Türkçe kurulum: https://github.com/mega-chizi/MangaTranslateLLM/tree/main/README/tr Visit the GitHub repository (https://github.com/mega-chizi/MangaTranslateLLM) for the full source code, detailed explanation of how the translation pipeline works, and support options.
Aug 17, 2026
rating_count is the Chrome Web Store ratings count, not a written-review count.
Media assets
Screenshots and videos on the listing.
Has promo video
Whether the listing includes at least one video.
Languages
Declared language locales.
Developer website
Listing exposes a developer website URL.
Contact email
Listing exposes a contact email.
Keyword in name
Case-insensitive substring match in the name.
Keyword in description
Case-insensitive substring match in the description.
Keyword occurrences in description
Count of case-insensitive occurrences in the description.
Category user-count percentile
Share of same-category extensions with fewer users (null if unknown).
These are transparent listing completeness / keyword signals, not a prediction of Chrome Web Store search ranking.