Compact: 1 to 10 billion
Phi, Gemma, Llama 3 8B, Mistral 7B and most on-device and edge models. 82 models.
WorldPaliGemma
A 3B open vision-language model built on SigLIP and Gemma-2BMultimodal · Open weights · 2024
🇮🇳 IndiaShuka v1
Audio-native language model for Indic languagesMultimodal · Open weights
WorldDeepSeek-OCR
Optical character recognition model using visual compressionMultimodal · Open weights · 2025