| 1 | kosmos-2.5microsoft | Image Text to Text | 4,637 | +4,637 | 271 | 1.4B |
| 2 | wav2vec2-ljspeech-gruutbookbot | Speech Recognition | 4,636 | +4,636 | 16 | 94.4M |
| 3 | gliner-ja-pii-v1DataSign | Token Classification | 4,633 | +4,633 | 3 | — |
| 4 | OlmoEarth-v1-Baseallenai | — | 4,630 | +4,630 | 41 | — |
| 5 | chinese-roberta-wwm-ext-largehfl | Fill Mask | 4,625 | +4,625 | 234 | — |
| 6 | distil-wav2vec2-adult-child-cls-37mbookbot | Audio Classification | 4,623 | +4,623 | 2 | 37.9M |
| 7 | HunyuanVideo1.5DeepBeepMeep | — | 4,622 | +4,622 | 2 | — |
| 8 | scinclmalteos | Embeddings | 4,621 | +4,621 | 35 | 110M |
| 9 | chronos-t5-miniautogluon | Time Series Forecasting | 4,620 | +4,620 | 5 | 20.5M |
| 10 | finbert-finnsentimentfergusq | Text Classification | 4,619 | +4,619 | 2 | 125M |
| 11 | GLuCoSE-base-japkshatech | Sentence Similarity | 4,618 | +4,618 | 34 | — |
| 12 | blip2-itm-vit-gSalesforce | Zero-Shot Image Classification | 4,618 | +4,618 | 3 | 1.2B |
| 13 | lotusComfy-Org | — | 4,614 | +4,614 | 6 | — |
| 14 | control_v11f1p_sd15_depthlllyasviel | Image To Image | 4,614 | +4,614 | 67 | 361M |
| 15 | Qwen3-Embedding-0.6B-4bit-DWQmlx-community | Text Generation | 4,613 | +4,613 | 15 | 596M |
| 16 | Gemory-26B-A4B-GGUFUltimateIntent | Text Generation | 4,613 | +4,613 | 32 | — |
| 17 | Sentence-Level-Stereotype-Detectorwu981526092 | Text Classification | 4,611 | +4,611 | 6 | — |
| 18 | inception_v3.tv_in1ktimm | Image Classification | 4,610 | +4,610 | 1 | 23.9M |
| 19 | tf_efficientnetv2_m.in21k_ft_in1ktimm | Image Classification | 4,609 | +4,609 | 5 | 54.4M |
| 20 | all-MiniLM-L6-v2-onnxonnx-models | Sentence Similarity | 4,609 | +4,609 | 16 | — |
| 21 | Qwen1.5-4B-ChatQwen | Text Generation | 4,607 | +4,607 | 46 | 4B |
| 22 | textnet-baseczczup | Image Feature Extraction | 4,607 | +4,607 | 4 | 13.6M |
| 23 | all-MiniLM-L6-v2-ONNXonnx-community | Sentence Similarity | 4,605 | +4,605 | 5 | — |
| 24 | FLUX.2-dev-NVFP4black-forest-labs | Image To Image | 4,603 | +4,603 | 110 | — |
| 25 | metricgan-plus-voicebankspeechbrain | Audio to Audio | 4,600 | +4,600 | 72 | — |
| 26 | Qwen3.8-27B-i1-IQ4_XS-GGUF-Smallerjrell | — | 4,599 | +4,599 | 95 | — |
| 27 | AIKIAviv | Text Classification | 4,598 | +4,598 | 0 | 113M |
| 28 | Llama-2-7B-GGUFTheBloke | Text Generation | 4,598 | +4,598 | 207 | — |
| 29 | nucleotide-transformer-v2-100m-multi-speciesInstaDeepAI | Fill Mask | 4,598 | +4,598 | 2 | 97.9M |
| 30 | Qwen3.8-2B-Uncensored-GGUFatakhadivi | Text Generation | 4,588 | +4,588 | 21 | — |
| 31 | Qwen2.5-32B-AGI-GGUFbartowski | Text Generation | 4,582 | +4,582 | 42 | — |
| 32 | ruri-v3-30m-ONNXsirasagi62 | Embeddings | 4,581 | +4,581 | 2 | — |
| 33 | Ling-3.0-tiny-GGUFinclusionAI | Text Generation | 4,581 | +4,581 | 38 | — |
| 34 | stable-diffusion-3.5-large-GGUFsecond-state | Text to Image | 4,580 | +4,580 | 18 | — |
| 35 | ettin-encoder-150mjhu-clsp | Fill Mask | 4,569 | +4,569 | 14 | — |
| 36 | superglue_indoormagic-leap-community | — | 4,568 | +4,568 | 3 | 13.3M |
| 37 | MS3.2-PaintedFantasy-v4.1-24B-GGUFzerofata | — | 4,567 | +4,567 | 10 | — |
| 38 | needle2Cactus-Compute | Text Generation | 4,566 | +4,566 | 332 | — |
| 39 | Mistral-7B-Instruct-v0.2-llamafilemozilla-ai | Text Generation | 4,564 | +4,564 | 26 | — |
| 40 | Phi-3.5-MoE-instruct-GGUFbartowski | Text Generation | 4,564 | +4,564 | 15 | — |
| 41 | klue-roberta-news-sentimentFISA-conclave | Text Classification | 4,563 | +4,563 | 0 | 111M |
| 42 | OpenMed-PII-BioClinicalModern-Large-395M-v1OpenMed | Token Classification | 4,560 | +4,560 | 10 | 396M |
| 43 | Qwen3.8-Flash-Next-oQ4e-mtpJundot | — | 4,559 | +4,559 | 75 | 180B |
| 44 | sam3-litetext-s0vil-uob | Mask Generation | 4,558 | +4,558 | 20 | 529M |
| 45 | gpt2-chinese-cluecorpussmalluer | Text Generation | 4,557 | +4,557 | 263 | — |
| 46 | hrnet_w18.ms_aug_in1ktimm | Image Classification | 4,553 | +4,553 | 3 | 21.4M |
| 47 | pcad2-200M-cnet-baselineemarro | Embeddings | 4,552 | +4,552 | 0 | 258M |
| 48 | Qwen3.8-27B-ROCmFP4-STRIX-MTP-GGUFkingjones777 | Text Generation | 4,551 | +4,551 | 38 | — |
| 49 | SocRoBERTa-socialESGBERT | Text Classification | 4,549 | +4,549 | 0 | — |
| 50 | tiny-random-VisionEncoderDecoderModel-donutoptimum-internal-testing | Image Text to Text | 4,549 | +4,549 | 0 | 3.9M |