LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit Text Generation âĒ 0.2B âĒ Updated 22 days ago âĒ 512 âĒ 5
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper âĒ 2503.11576 âĒ Published Mar 14, 2025 âĒ 156
docling-project/SmolDocling-256M-preview Image-Text-to-Text âĒ Updated Sep 17, 2025 âĒ 67.3k âĒ 1.61k
Running on Zero Featured 260 SmolDocling ðĶ 260 Convert images and queries into structured document text