/ Docs / Models

Models

Playto automatically downloads and manages the AI models. No manual setup required.

Engine Tiers

Tier Mode Size VRAM Best For
Lightweight Text Reading ~3 GB ~2 GB Fast OCR translation for all languages.
Lightweight Vision Image Recognition ~3 GB ~2 GB Image Recognition at low VRAM cost.
High Quality Image Recognition ~6 GB ~5 GB Uses a larger model for heavier inference. May produce better output for complex text, but not guaranteed.
Cloud AI Both N/A 0 GB No GPU needed. Free tier available.
Text Reading and Lightweight Vision share the same base model. Switching between them doesn't require a separate download.

Language-Specific Picks

Playto ships separate models tuned for Latin scripts (English, European) and CJK scripts (Japanese, Chinese, Korean). The right model is selected automatically based on your source language — no manual choice required.

VRAM Performance Guide

Available VRAM Recommendation
4 GB Lightweight. Text Reading and Lightweight Vision work well alongside most games.
6-8 GB High Quality Image Recognition for demanding scenes. Text Reading + Vision both work well.
12 GB+ Any model. Game and AI run comfortably side by side.
No GPU Cloud AI. Zero local VRAM, free tiers available. See Cloud AI setup guide.

Remember: your game also uses VRAM. The numbers above are VRAM available in addition to what your game needs. Playto auto-fits GPU Layers based on available VRAM, but you can override in Settings if needed.