| 1 | clefCloudflareimage text to text · 27B · transformers | image text to text · 27B · transformers | 1,760 | – | – | 1581 |
| 2 | JEV-27B-VLautotrustimage text to text · 28B · transformers | image text to text · 28B · transformers | 1,460 | – | – | 1211 |
| 3 | | text classification · 26B · transformers | 982 | – | – | 818 |
| 4 | | feature extraction · 744M · transformers | 787 | – | – | 769 |
| 5 | Kolibri-1Aleph-Alphatext generation · 78B · vllm | text generation · 78B · vllm | 754 | – | – | 721 |
| 6 | | text to image · gguf | 3,514 | – | – | 683 |
| 7 | | text generation · transformers | 613 | – | – | 588 |
| 8 | clef-flashCloudflareimage text to text · 9.4B · transformers | image text to text · 9.4B · transformers | 633 | – | – | 576 |
| 9 | LTX-2.5Lightricksimage to video · diffusion-single-file | image to video · diffusion-single-file | 6,733 | – | – | 494 |
| 10 | layaconvaiinnovationstext classification · 421M · transformers | text classification · 421M · transformers | 5,316 | – | – | 473 |
| 11 | humanizerjialinyyzztext generation · 12B · gguf | text generation · 12B · gguf | 430 | – | – | 420 |
| 12 | | image text to text · 28B · transformers | 17,165 | – | – | 339 |
| 13 | | image text to text · gguf | 673 | – | – | 235 |
| 14 | | text to image · 7.1B · diffusers | 3,067 | – | – | 232 |
| 15 | | text generation · 146B · exllamav3 | 275 | – | – | 215 |
| 16 | | image text to text · 9.8B | 2,897 | – | – | 196 |
| 17 | | text to speech | 211 | – | – | 196 |
| 18 | | text generation · llama.cpp | 441 | – | – | 192 |
| 19 | | image classification | 443 | – | – | 189 |
| 20 | Phonon-2FermionResearchautomatic speech recognition · mlx | automatic speech recognition · mlx | 267 | – | – | 188 |
| 21 | | image text to text · 180B · transformers | 6,001 | – | – | 187 |
| 22 | | image to image · diffusers | 1,276 | – | – | 171 |
| 23 | | image text to text · 763B · transformers | 4,207 | – | – | 166 |
| 24 | | text generation · llama.cpp | 2,509 | – | – | 157 |
| 25 | | image text to text | 1,529 | – | – | 154 |
| 26 | | image text to text · gguf | 2,016 | – | – | 149 |
| 27 | | text to image · 7.1B · diffusers | 647 | – | – | 148 |
| 28 | | image text to video · minimax-h3 | 240 | – | – | 141 |
| 29 | | voice activity detection · 99M · nemo | 739 | – | – | 140 |
| 30 | | image text to text · gguf | 327 | – | – | 139 |
| 31 | | feature extraction | 139 | – | – | 139 |
| 32 | | text classification · 14B · transformers | 151 | – | – | 135 |
| 33 | whistleCactus-Computeautomatic speech recognition · cactus-needle | automatic speech recognition · cactus-needle | 134 | – | – | 132 |
| 34 | | image text to text · gguf | 627 | – | – | 128 |
| 35 | | video to video · diffusion-single-file | 345 | – | – | 128 |
| 36 | MiniMax-H3MiniMaxAIimage text to video · 33B · minimax-h3 | image text to video · 33B · minimax-h3 | 5,951 | – | – | 123 |
| 37 | | text ranking · contrastive-lm | 744 | – | – | 123 |
| 38 | | token classification · 486M · gliner2 | 387 | – | – | 122 |
| 39 | Julia-1SupersonicLabstext classification · 144M · pytorch | text classification · 144M · pytorch | 463 | – | – | 120 |
| 40 | | | 4,911 | – | – | 118 |
| 41 | | 4.7B | 119 | – | – | 117 |
| 42 | | image text to text · gguf | 126 | – | – | 117 |
| 43 | | text generation · 753B · transformers | 336 | – | – | 115 |
| 44 | | text generation · gguf | 289 | – | – | 108 |
| 45 | | automatic speech recognition · pyannote-audio | 2,591 | – | – | 106 |
| 46 | sam3facebookmask generation · 860M · transformers | mask generation · 860M · transformers | 3,850 | – | – | 106 |
| 47 | GLM-5.3zai-orgtext generation · 753B · transformers | text generation · 753B · transformers | 2,124 | – | – | 102 |
| 48 | PrismFrancisRingimage to video · diffusers | image to video · diffusers | 103 | – | – | 102 |
| 49 | | text generation · llama.cpp | 1,476 | – | – | 97 |
| 50 | JEV-9Bautotrusttext classification · 9.0B · transformers | text classification · 9.0B · transformers | 133 | – | – | 95 |