view post Post 9571 deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️ > pretty insane it can parse and re-render charts in HTML> it uses CLIP and SAM features concatenated, so better grounding> very efficient per vision tokens/performance ratio> covers 100 languages See translation
Mar 6 Releases tencent/Penguin-VL-2B Text Generation • 2B • Updated 2 days ago • 326 • 22 KORMo-VL/KORMo-VL-Diffusion Updated 6 days ago • 9 • 15 Lightricks/LTX-2.3 Image-to-Video • Updated 6 days ago • 345k • 474 sarvamai/sarvam-30b Text Generation • 32B • Updated about 22 hours ago • 6.31k • 144
Feb 27 Releases Qwen/Qwen3.5-122B-A10B-FP8 Image-Text-to-Text • 125B • Updated 13 days ago • 117k • 63 cyankiwi/Qwen3.5-27B-AWQ-BF16-INT4 Image-Text-to-Text • 12B • Updated 14 days ago • 26.8k • 25 Aratako/Irodori-TTS-500M Text-to-Speech • 0.5B • Updated 14 days ago • 47 LiconStudio/VBVR-wan2.2-comfy-bf16 Updated 13 days ago • 3.51k • 21
Mar 6 Releases tencent/Penguin-VL-2B Text Generation • 2B • Updated 2 days ago • 326 • 22 KORMo-VL/KORMo-VL-Diffusion Updated 6 days ago • 9 • 15 Lightricks/LTX-2.3 Image-to-Video • Updated 6 days ago • 345k • 474 sarvamai/sarvam-30b Text Generation • 32B • Updated about 22 hours ago • 6.31k • 144
Feb 27 Releases Qwen/Qwen3.5-122B-A10B-FP8 Image-Text-to-Text • 125B • Updated 13 days ago • 117k • 63 cyankiwi/Qwen3.5-27B-AWQ-BF16-INT4 Image-Text-to-Text • 12B • Updated 14 days ago • 26.8k • 25 Aratako/Irodori-TTS-500M Text-to-Speech • 0.5B • Updated 14 days ago • 47 LiconStudio/VBVR-wan2.2-comfy-bf16 Updated 13 days ago • 3.51k • 21
Running on CPU Upgrade 18 Daggr Image To 3d 👀 Convert images into 3D assets with background removal and enhancement
Running on Zero Featured 108 SAM3 Video Segmentation 🐠 Track and label objects in videos using text prompts or clicks