moonshotai/Kimi-VL-A3B-Thinking-2506

Image-Text-to-Text • Updated about 1 month ago • 17.8k • 352

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 Jun 20, 2025 • 17.1k • 1.59k

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