| 1 | wan-ggufcalcuis | Text to Video | 4,100 | +4,100 | 207 | — |
| 2 | surya_layout2datalab-to | Object Detection | 4,098 | +4,098 | 7 | — |
| 3 | Qwen3-Coder-30B-A3B-Instruct-1M-GGUFunsloth | Text Generation | 4,094 | +4,094 | 165 | — |
| 4 | msmarco-MiniLM-L6-cos-v5sentence-transformers | Sentence Similarity | 4,091 | +4,091 | 12 | 22.7M |
| 5 | ast-finetuned-audioset-10-10-0.4593Xenova | Audio Classification | 4,091 | +4,091 | 0 | — |
| 6 | Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-GGUFhuihui-ai | Any to Any | 4,090 | +4,090 | 68 | — |
| 7 | YiSM-34B-0rnaltomek | Text Generation | 4,089 | +4,089 | 2 | 34.4B |
| 8 | vit_base_r50_s16_384.orig_in21k_ft_in1ktimm | Image Classification | 4,089 | +4,089 | 4 | 99M |
| 9 | Qwen2.5-Coder-7B-bnb-4bitunsloth | Text Generation | 4,088 | +4,088 | 19 | 7.8B |
| 10 | kpfbertjinmang2 | Embeddings | 4,087 | +4,087 | 4 | 113M |
| 11 | MiniCPM3-4Bopenbmb | Text Generation | 4,087 | +4,087 | 421 | — |
| 12 | clip-ViT-B-32-textQdrant | Sentence Similarity | 4,082 | +4,082 | 3 | — |
| 13 | resnet152.tv2_in1ktimm | Image Classification | 4,080 | +4,080 | 0 | 60.3M |
| 14 | Qwen3.5-0.8B-GGUFlmstudio-community | — | 4,079 | +4,079 | 17 | — |
| 15 | Arabic-SBERT-100Kakhooli | Sentence Similarity | 4,078 | +4,078 | 17 | 135M |
| 16 | NVIDIA-Nemotron-Parse-2.0nvidia | Image Text to Text | 4,078 | +4,078 | 118 | 903M |
| 17 | sandboxLeFeujitif | Text to Image | 4,078 | +4,078 | 3 | — |
| 18 | GPT-OSS-20B-NPU2FastFlowLM | Text Generation | 4,077 | +4,077 | 1 | — |
| 19 | vit-gpt2-image-captioningXenova | Image to Text | 4,075 | +4,075 | 30 | — |
| 20 | pixel-art-xlnerijs | Text to Image | 4,075 | +4,075 | 656 | — |
| 21 | Qwen-Image-2512-GGUFbyteshape | Text to Image | 4,072 | +4,072 | 9 | — |
| 22 | OpenMed-ZeroShot-NER-Genomic-Base-220MOpenMed | Token Classification | 4,072 | +4,072 | 0 | — |
| 23 | japanese-reranker-cross-encoder-xsmall-v1hotchpotch | Text Ranking | 4,071 | +4,071 | 7 | 107M |
| 24 | bert-base-arabic-camelbert-msa-nerCAMeL-Lab | Token Classification | 4,070 | +4,070 | 8 | — |
| 25 | TurboWan2.2-I2V-A14B-720P-ComfyUI-GGUFvantagewithai | Image To Video | 4,068 | +4,068 | 2 | — |
| 26 | OpenMed-ZeroShot-NER-BloodCancer-XLarge-770MOpenMed | Token Classification | 4,067 | +4,067 | 0 | — |
| 27 | Meta-Llama-3.1-8B-Instruct-FP8-dynamicRedHatAI | Text Generation | 4,066 | +4,066 | 9 | 8B |
| 28 | sup-simcse-bert-base-uncasedprinceton-nlp | Embeddings | 4,064 | +4,064 | 26 | — |
| 29 | Qwen2.5-7B-Instruct-4bitmlx-community | Text Generation | 4,061 | +4,061 | 17 | 7.6B |
| 30 | chexpert-mimic-cxr-findings-baselineIAMJB | Image to Text | 4,057 | +4,057 | 2 | 61.3M |
| 31 | Aurora-Spec-Minimax-M2.5togethercomputer | Text Generation | 4,056 | +4,056 | 6 | 858M |
| 32 | stt-2.6b-en-trfskyutai | Speech Recognition | 4,055 | +4,055 | 10 | 2.7B |
| 33 | codet5p-110m-embeddingSalesforce | — | 4,052 | +4,052 | 69 | — |
| 34 | OpenMed-PII-French-ClinicalLongformer-Base-149M-v1OpenMed | Token Classification | 4,049 | +4,049 | 0 | 148M |
| 35 | aesthetics-predictor-v2-sac-logos-ava1-l14-linearMSEshunk031 | Embeddings | 4,046 | +4,046 | 10 | 305M |
| 36 | granite-4.0-1bibm-granite | Text Generation | 4,045 | +4,045 | 56 | 1.6B |
| 37 | Infinity-Instruct-7M-Gen-Llama3_1-8BBAAI | — | 4,043 | +4,043 | 11 | 8B |
| 38 | Qwen2-VL-2B-Instruct-GGUFbartowski | Image Text to Text | 4,041 | +4,041 | 37 | — |
| 39 | LTX-2.5-GGUFvantagewithai | Image To Video | 4,036 | +4,036 | 9 | — |
| 40 | jina-embeddings-v2-base-zhjinaai | Embeddings | 4,035 | +4,035 | 245 | 161M |
| 41 | paligemma2-3b-ft-docci-448google | Image Text to Text | 4,033 | +4,033 | 15 | 3B |
| 42 | granite-guardian-3.2-3b-a800mibm-granite | Text Generation | 4,033 | +4,033 | 8 | 3.3B |
| 43 | roberta-large-finetuned-csqadanlou | Multiple Choice | 4,032 | +4,032 | 0 | — |
| 44 | Qwen2.5-3B-GGUFbartowski | Text Generation | 4,031 | +4,031 | 6 | — |
| 45 | R3GE_Quen2.5_7BJackFRost0703 | — | 4,030 | +4,030 | 1 | — |
| 46 | gigaam-v3-rnnt-ggufhandy-computer | Speech Recognition | 4,030 | +4,030 | 0 | — |
| 47 | Fun-ASR-Nano-2512-ggufhandy-computer | Speech Recognition | 4,029 | +4,029 | 0 | — |
| 48 | SexGod_NSFW_Female_Nudes_QWEN_Image_Edit_2511Baraje | Text to Image | 4,029 | +4,029 | 35 | — |
| 49 | mms-tts-urdu-vits_finetunedsyedmuhammad | — | 4,028 | +4,028 | 0 | 83M |
| 50 | Huihui-Qwen3-VL-4B-Instruct-abliteratedhuihui-ai | Image Text to Text | 4,027 | +4,027 | 112 | 4.4B |