| 1 | BiomedNLP-BiomedBERT-base-uncased-abstractmicrosoft | Fill Mask | 717.7K | — | 96 | — |
| 2 | e5-small-v2intfloat | Sentence Similarity | 713K | — | 122 | 33.4M |
| 3 | models-movedggml-org | — | 712.8K | — | 14 | — |
| 4 | gemma-2-2b-itgoogle | Text Generation | 710.8K | — | 1,456 | 2.6B |
| 5 | distiluse-base-multilingual-cased-v2sentence-transformers | Sentence Similarity | 709K | — | 209 | 135M |
| 6 | GOT-OCR2_0stepfun-ai | Image Text to Text | 708.5K | — | 1,554 | 716M |
| 7 | wav2vec2-xls-r-300m-ftspeechsaattrupdan | Speech Recognition | 704.8K | — | 0 | 315M |
| 8 | Qwen2.5-1.5B-Instruct-AWQQwen | Text Generation | 703.9K | — | 7 | 1.8B |
| 9 | llama-nemotron-embed-1b-v2nvidia | Embeddings | 701.3K | — | 61 | 1.2B |
| 10 | phi-4microsoft | Text Generation | 699.6K | — | 2,290 | 14.7B |
| 11 | VibeVoice-ASRmicrosoft | Speech Recognition | 698.1K | — | 1,276 | 8.7B |
| 12 | Qwen3-0.6B-FP8Qwen | Text Generation | 697.4K | — | 62 | 752M |
| 13 | gemma-4-E4B-it-qat-w4a16-ctgoogle | Any to Any | 696.4K | — | 15 | 8.7B |
| 14 | Qwen3.6-27B-MLX-8bitlmstudio-community | Image Text to Text | 696.3K | — | 15 | 8B |
| 15 | Flux2-Klein-9B-True-V2wikeeyang | Text to Image | 696.3K | — | 190 | — |
| 16 | sam-vit-basefacebook | Mask Generation | 692.7K | — | 172 | 93.7M |
| 17 | dinov3-vitl16-pretrain-lvd1689mfacebook | Image Feature Extraction | 689K | — | 532 | 303M |
| 18 | parakeet-tdt-0.6b-v3-ggufhandy-computer | Speech Recognition | 684.4K | — | 1 | — |
| 19 | whisper-tiny.enXenova | Speech Recognition | 680K | — | 27 | — |
| 20 | bigvgan_v2_44khz_128band_512xnvidia | Audio to Audio | 671.6K | — | 77 | — |
| 21 | Qwen3.6-27B-MLX-4bitlmstudio-community | Image Text to Text | 669.5K | — | 16 | 4.7B |
| 22 | Qwen3.8-27B-NVFP4Inferact | Image Text to Text | 667.8K | — | 12 | 17.6B |
| 23 | vit_tiny_patch16_224.augreg_in21k_ft_in1ktimm | Image Classification | 667.6K | — | 4 | 5.7M |
| 24 | bert-log-anomaly-detectionAungMoonLord | Text Classification | 667.3K | — | 1 | 109M |
| 25 | Florence-2-largemicrosoft | Image Text to Text | 667K | — | 1,848 | 777M |
| 26 | deepseek-vl2-tinydeepseek-ai | Image Text to Text | 666.8K | — | 249 | 3.4B |
| 27 | bert_uncased_L-2_H-128_A-2google | — | 666.2K | — | 36 | 4.4M |
| 28 | Llama-3.1-Nemotron-Nano-VL-8B-V1nvidia | Image Text to Text | 665.7K | — | 181 | 8.7B |
| 29 | MiniCPM-V-4.6openbmb | Image Text to Text | 662.1K | — | 1,192 | 1.3B |
| 30 | manga-ocr-basekha-white | Image to Text | 659.4K | — | 178 | — |
| 31 | Llama-3.1-70B-Instructmeta-llama | Text Generation | 657.2K | — | 956 | 70.6B |
| 32 | Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF0bserverx | Text Generation | 654.8K | — | 257 | — |
| 33 | RMBG-2.0briaai | Image Segmentation | 654.6K | — | 1,376 | 221M |
| 34 | gemma-2-9b-itgoogle | Text Generation | 654.5K | — | 906 | 9.2B |
| 35 | FLUX.2-devblack-forest-labs | Image To Image | 654.3K | — | 2,083 | 32.2B |
| 36 | Qwen2.5-72B-Instruct-AWQQwen | Text Generation | 653.9K | — | 78 | 73B |
| 37 | Llama-3.2-1B-Instruct-FP8-dynamicRedHatAI | Text Generation | 653.1K | — | 4 | 1.5B |
| 38 | DeepSeek-R1-Distill-Qwen-14Bdeepseek-ai | Text Generation | 649.9K | — | 673 | 14.8B |
| 39 | FLUX.1-devblack-forest-labs | Text to Image | 649.6K | — | 14.2K | 11.9B |
| 40 | KoELECTRA-small-v3-modu-nerLeo97 | Token Classification | 645.9K | — | 25 | 14.1M |
| 41 | vit_small_patch16_224.augreg_in21k_ft_in1ktimm | Image Classification | 645.1K | — | 4 | 22.1M |
| 42 | bert-base-arabertv02aubmindlab | Fill Mask | 644.6K | — | 48 | 136M |
| 43 | esm2_t6_8M_UR50Dfacebook | Fill Mask | 643.4K | — | 36 | 7.8M |
| 44 | flash-attn3kernels-community | — | 642.2K | — | 49 | — |
| 45 | NVIDIA-Nemotron-3-Nano-30B-A3B-FP8nvidia | Text Generation | 641.2K | — | 357 | 31.6B |
| 46 | Qwen3-VL-8B-Instruct-abliterated-GGUFmradermacher | — | 641.1K | — | 9 | — |
| 47 | specter2_baseallenai | Embeddings | 640.7K | — | 48 | — |
| 48 | Phi-3.5-mini-instructmicrosoft | Text Generation | 640.2K | — | 1,068 | 3.8B |
| 49 | Huihui-Qwen3.6-27B-abliterated-AWQ-MTPshawnw3i | Image Text to Text | 639.9K | — | 13 | 6.3B |
| 50 | Qwen3-ForcedAligner-0.6BQwen | Speech Recognition | 639.3K | — | 153 | 918M |