| 1 | deepforest-treeweecology | — | 157.3K | — | 10 | 32.3M |
| 2 | convnext_tiny.fb_in22k_ft_in1ktimm | Image Classification | 157.1K | — | 0 | 28.6M |
| 3 | ViT-B-16-SigLIPtimm | Zero-Shot Image Classification | 156.7K | — | 40 | — |
| 4 | surya_ordervikp | — | 156.5K | — | 2 | 137M |
| 5 | OpenMed-NER-SpeciesDetect-ModernClinical-395MOpenMed | Token Classification | 156.4K | — | 0 | 396M |
| 6 | opus-mt-tc-big-en-trHelsinki-NLP | Translation | 156.3K | — | 58 | — |
| 7 | Qwen3-ASR-0.6B-ggufhandy-computer | Speech Recognition | 156.1K | — | 1 | — |
| 8 | opus-mt-ROMANCE-enHelsinki-NLP | Translation | 156.1K | — | 9 | — |
| 9 | Qwen3-Coder-Next-NVFP4-GB10gdubicki | Text Generation | 155.8K | — | 3 | — |
| 10 | snowflake-arctic-embed-m-v2.0Snowflake | Sentence Similarity | 155.6K | — | 107 | 305M |
| 11 | Idefics3-8B-Llama3HuggingFaceM4 | Image Text to Text | 155.6K | — | 305 | 8.5B |
| 12 | RolmOCRreducto | Image Text to Text | 155.5K | — | 589 | 8.3B |
| 13 | DeepSeek-Coder-V2-Lite-Instruct-FP8RedHatAI | Text Generation | 155.4K | — | 14 | 15.7B |
| 14 | Qwen3.5-9B-AWQ-4bitcyankiwi | Image Text to Text | 155.4K | — | 37 | 9.9B |
| 15 | Apertus-70B-Instruct-2509-quantized.w4a16RedHatAI | Text Generation | 155.3K | — | 2 | 11.3B |
| 16 | Llama-3.1-405Bmeta-llama | Text Generation | 155.3K | — | 987 | 406B |
| 17 | opus-mt-tc-big-tr-enHelsinki-NLP | Translation | 155.1K | — | 101 | 235M |
| 18 | higgs-audio-v2-tokenizerbosonai | Embeddings | 155.1K | — | 59 | 201M |
| 19 | GOT-OCR-2.0-hfstepfun-ai | Image Text to Text | 154.9K | — | 240 | 561M |
| 20 | GigaChat3.1-Audio-10B-A1.8Bai-sage | Text Generation | 154.8K | — | 51 | — |
| 21 | mobilenetv4_conv_small.e2400_r224_in1ktimm | Image Classification | 154.6K | — | 12 | 3.8M |
| 22 | gemma-2b-itgoogle | Text Generation | 154.6K | — | 942 | 2.5B |
| 23 | Molmo2-8Ballenai | Image Text to Text | 154.5K | — | 192 | 8.7B |
| 24 | vit_large_patch14_dinov2.lvd142mtimm | Image Feature Extraction | 154.5K | — | 17 | 304M |
| 25 | NVIDIA-Nemotron-3-Super-120B-A12B-FP8nvidia | Text Generation | 154.5K | — | 276 | 124B |
| 26 | wildguardallenai | Text Generation | 154.5K | — | 57 | 7.2B |
| 27 | gemma-3-12b-it-int4-awqgaunernst | Image Text to Text | 154.3K | — | 24 | 12.2B |
| 28 | segformer-b0-finetuned-ade-512-512Xenova | Image Segmentation | 154K | — | 2 | — |
| 29 | z_imageComfy-Org | — | 153.9K | — | 259 | — |
| 30 | vit_base_patch16_224.dinotimm | Image Feature Extraction | 153.7K | — | 6 | 85.8M |
| 31 | multilingual-e5-smallXenova | Embeddings | 153.5K | — | 17 | — |
| 32 | nllb-200-3.3Bfacebook | Translation | 153.5K | — | 472 | — |
| 33 | Voxtral-Small-24B-2507-ggufhandy-computer | Speech Recognition | 153.3K | — | 0 | — |
| 34 | Qwen1.5-0.5B-ChatQwen | Text Generation | 153.2K | — | 99 | 620M |
| 35 | Meta-Llama-3-70Bmeta-llama | Text Generation | 153.2K | — | 879 | 70.6B |
| 36 | Qwen3-ForcedAligner-0.6B-hfQwen | Token Classification | 153.1K | — | 32 | 918M |
| 37 | GLM-4.5-Airzai-org | Text Generation | 153.1K | — | 636 | 110B |
| 38 | Inklingthinkingmachines | Image Text to Text | 153K | — | 1,744 | 952B |
| 39 | Qwen3.5-122B-A10B-MTP-GGUFunsloth | Image Text to Text | 152.7K | — | 98 | — |
| 40 | Llama-Guard-4-12Bmeta-llama | Image Text to Text | 152.5K | — | 119 | 12B |
| 41 | Kimi-K2.5-NVFP4nvidia | Text Generation | 152.3K | — | 86 | — |
| 42 | Gemma-4-E2B-Uncensored-HauhauCS-AggressiveHauhauCS | Image Text to Text | 152.3K | — | 291 | — |
| 43 | Llama-3.2-1B-Instruct-GGUFbartowski | Text Generation | 152K | — | 176 | — |
| 44 | opus-mt-en-esHelsinki-NLP | Translation | 151.8K | — | 122 | — |
| 45 | trocr-large-handwrittenmicrosoft | Image to Text | 151.5K | — | 166 | — |
| 46 | granite-speech-4.1-2b-plusibm-granite | Speech Recognition | 151.4K | — | 88 | 2.1B |
| 47 | vit_base_patch16_224.augreg_in21k_ft_in1ktimm | Image Classification | 151K | — | 0 | 86.6M |
| 48 | medasrgoogle | Speech Recognition | 150.7K | — | 359 | 105M |
| 49 | paraphrase-multilingual-minilm-l12-v3-mngmunkhtur | Sentence Similarity | 150.6K | — | 0 | 118M |
| 50 | PP-LCNet_x1_0_textline_oriPaddlePaddle | Image to Text | 150.6K | — | 7 | — |