Hardware Compatibility and Stable Setup

This page covers the hardware cases users ask about most: laptops without dedicated GPUs, RTX 5000 series cards, OCR device choices, and how Thaluna handles non-ASCII Windows usernames.

Hardware and OCR Settings

Thaluna performance options for OCR and translation devices — Choose OCR and translation devices, low CPU mode, and other performance settings based on your hardware.

Thaluna OCR language selection settings — OCR language and OCR mode matter as much as hardware selection when text quality is poor.

Low-end laptops without dedicated GPU

Thaluna can still run without a dedicated GPU. OCR works on CPU. Local translation on CPU will be slower, so OpenRouter or Ollama is usually the better translation path.

RTX 5000 series GPUs

Due to upstream framework limitations, built-in OCR acceleration for PaddleOCR and MangaOCR is not currently available on RTX 5000 series GPUs. Recommended setup: OCR Device → CPU, Translation Device → CPU, then use Ollama or OpenRouter.

Non-ASCII Windows usernames

If your Windows username contains Cyrillic, Arabic, or other non-ASCII characters, Thaluna automatically switches its data path to C:\Users\Public\Thaluna. No manual action is required.

General startup and GPU issues

If you see missing DLL or ImportError problems, install Microsoft Visual C++ Redistributable (x64), update your NVIDIA drivers if applicable, and restart the PC after installation.

Stable fallback setup

OCR Device → CPU when GPU OCR is unstable or unsupported
Use Ollama for GPU-accelerated translation on supported systems
Use OpenRouter when you want cloud translation that does not depend on local GPU runtime