SAVRN Model Hub
Open-Weight Models by Task
Every task in the library, with how many models each one covers. Each page lists them by demand, with their size, license, files and the GPUs they need.
- Text generation 338
- Image and text to text 138
- Robotics 81
- Speech recognition 78
- Feature extraction 77
- Sentence similarity 73
- Image segmentation 67
- Text to speech 64
- Image classification 63
- Any to any 61
- Token classification 61
- Translation 61
- Audio classification 60
- Time series forecasting 60
- Object detection 58
- Text to image 58
- Video classification 58
- Zero-shot classification 56
- Fill mask 55
- Question answering 53
- Text classification 48
- Image to text 47
- Summarization 41
- Text to video 40
- Tabular classification 36
- Image to video 18
- Text ranking 18
- Zero shot image classification 17
- Reinforcement learning 8
- Image to image 7
- Image feature extraction 6
- Image text to video 6
- Image to 3d 3
- Voice activity detection 3
- Zero shot object detection 3
- Audio text to text 2
- Audio to audio 2
- Depth estimation 2
- Graph ml 2
- Mask generation 2
- Tabular regression 2
- Text to audio 2
- Video text to text 2
- Document question answering 1
- Image text to image 1
- Keypoint detection 1
- Table question answering 1
- Unconditional image generation 1