playto / 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 ~3.3 GB ~1.5 GB Fast OCR translation for all languages. Included in Lite.
Lightweight Vision Image Recognition ~4.2 GB ~1.5 GB Same base model + vision adapter. Best for English & Latin scripts.
High Quality Image Recognition ~7 GB ~5.5 GB Best for CJK (Japanese, Chinese, Korean). Requires 6GB+ VRAM.
Cloud AI Both N/A 0 GB Gemini / OpenAI. 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

Source Language Text Reading Image Recognition
English & European Lightweight Lightweight Vision
Japanese / Chinese / Korean Lightweight High Quality or Cloud AI

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 CJK languages. Text Reading + Vision both work well.
12 GB+ Any model. Game and AI run comfortably side by side.
No GPU Cloud AI (Gemini Flash free tier). Zero local VRAM, fast cloud inference.

Remember: your game also uses VRAM. The numbers above are VRAM available in addition to what your game needs. Reduce GPU Layers in Settings if you run out of VRAM.