moonshotai/Kimi-VL-A3B-Thinking-2506

Image-Text-to-Text • 16B • Updated 22 days ago • 43.6k • 221

Note - powerful reasoning vision LM, 3B active params, smarter with less tokens, supports long documents, videos

nanonets/Nanonets-OCR-s

Image-Text-to-Text • 4B • Updated 28 days ago • 287k • 1.41k

Note 3.75B params OCR model based on Qwen2.5VL-3B-Instruct (OS)