| 1 | MiniCPM-SALA-AWQ-8bitcyankiwi | Text Generation | 149.7K | +149.7K | 0 | 3.1B |
| 2 | unifiedqa-t5-smallallenai | — | 149.1K | +149.1K | 5 | — |
| 3 | Qwen2.5-1.5BQwen | Text Generation | 148.8K | +148.8K | 227 | 1.5B |
| 4 | ms-marco-TinyBERT-L2-v2cross-encoder | Text Ranking | 148.2K | +148.2K | 44 | 4.4M |
| 5 | Qwen2.5-Coder-7BQwen | Text Generation | 147.8K | +147.8K | 177 | 7.6B |
| 6 | gliner2-base-v1fastino | — | 147.8K | +147.8K | 101 | 208M |
| 7 | blip-image-captioning-largeSalesforce | Image to Text | 147.6K | +147.6K | 1,488 | 470M |
| 8 | NVIDIA-Nemotron-Nano-9B-v2-FP8nvidia | Text Generation | 146.8K | +146.8K | 9 | 8.9B |
| 9 | NVIDIA-Nemotron-3-Nano-30B-A3B-BF16nvidia | Text Generation | 146.8K | +146.8K | 824 | 31.6B |
| 10 | GOT-OCR2_0stepfun-ai | Image Text to Text | 146.6K | +146.6K | 1,561 | 716M |
| 11 | all-roberta-large-v1sentence-transformers | Sentence Similarity | 146.1K | +146.1K | 66 | 355M |
| 12 | Laguna-S-2.1-GGUFpoolside | — | 145.9K | +145.9K | 178 | — |
| 13 | Qwen3-Coder-30B-A3B-Instruct-AWQQuantTrio | Text Generation | 145.3K | +145.3K | 11 | 30.5B |
| 14 | Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUFDavidAU | Image Text to Text | 145.2K | +145.2K | 2,411 | — |
| 15 | parakeet-tdt-0.6b-v3-ggufhandy-computer | Speech Recognition | 145.2K | +145.2K | 6 | — |
| 16 | DeepSeek-R1-0528-Qwen3-8Bdeepseek-ai | Text Generation | 145.1K | +145.1K | 1,092 | 8.2B |
| 17 | Qwen2.5-72B-Instruct-AWQQwen | Text Generation | 144.8K | +144.8K | 78 | 73B |
| 18 | Qwen3.5-9B-MLX-8bitlmstudio-community | Image Text to Text | 144.3K | +144.3K | 3 | 9.4B |
| 19 | Qwen3-Reranker-4B-W4A16-G128boboliu | Text Classification | 144.2K | +144.2K | 2 | 4.1B |
| 20 | indic-conformer-600m-multilingualai4bharat | Speech Recognition | 144K | +144K | 201 | — |
| 21 | all-MiniLM-L6-v2-GGUFleliuga | Sentence Similarity | 143.6K | +143.6K | 9 | — |
| 22 | FastVideo-FastH3-4-step-Preview-v1-VSA-DataFreeFastVideo | Text to Video | 143.6K | +143.6K | 318 | 35B |
| 23 | pythia-14mEleutherAI | Text Generation | 143.2K | +143.2K | 7 | 14.1M |
| 24 | tiny-clip-text-2peft-internal-testing | — | 143K | +143K | 2 | 69.5K |
| 25 | bert-base-multilingual-uncased-sentimentnlptown | Text Classification | 142.5K | +142.5K | 488 | 167M |
| 26 | MiniMax-H3DeepBeepMeep | — | 142.5K | +142.5K | 66 | — |
| 27 | Qwen3.6-35B-A3B-NVFP4-Fastunsloth | Image Text to Text | 142.2K | +142.2K | 120 | 21.8B |
| 28 | Qwen3-4B-GGUFQwen | Text Generation | 142.1K | +142.1K | 173 | — |
| 29 | vit_base_patch14_dinov2.lvd142mtimm | Image Feature Extraction | 142.1K | +142.1K | 10 | 86.6M |
| 30 | Qwen2.5-Coder-3B-InstructQwen | Text Generation | 141.7K | +141.7K | 131 | 3.1B |
| 31 | gte-Qwen2-1.5B-instructAlibaba-NLP | Sentence Similarity | 141.2K | +141.2K | 238 | 1.8B |
| 32 | deberta-v3-largemicrosoft | Fill Mask | 140.9K | +140.9K | 291 | — |
| 33 | tiny-random-LlamaForCausalLMhmellor | Text Generation | 140.4K | +140.4K | 2 | 1.1M |
| 34 | InternVL2-2BOpenGVLab | Image Text to Text | 140.3K | +140.3K | 83 | 2.2B |
| 35 | nli-deberta-v3-basecross-encoder | Zero-Shot Classification | 140.3K | +140.3K | 50 | 184M |
| 36 | Qwen3-1.7B-BaseQwen | Text Generation | 140.3K | +140.3K | 80 | 1.7B |
| 37 | tiny-random-LlamaForCausalLMoptimum-intel-internal-testing | — | 140K | +140K | 0 | — |
| 38 | PP-OCRv5_server_detPaddlePaddle | Image to Text | 139.4K | +139.4K | 75 | — |
| 39 | llama-nemotron-rerank-1b-v2nvidia | Text Ranking | 138.1K | +138.1K | 65 | 1.2B |
| 40 | whisper-medium-ggufhandy-computer | Speech Recognition | 138K | +138K | 0 | — |
| 41 | m2m100_418Mfacebook | — | 137.7K | +137.7K | 351 | — |
| 42 | Qwen3-ASR-0.6BQwen | Speech Recognition | 137.3K | +137.3K | 367 | 938M |
| 43 | gemma-4-E2B-it-qat-q4_0-ggufgoogle | Any to Any | 137.2K | +137.2K | 136 | — |
| 44 | minimax-h3-fused-turbo-int8-convrotMATLOWAI | Image Text To Video | 137.1K | +137.1K | 239 | — |
| 45 | Qwen2.5-Coder-1.5B-InstructQwen | Text Generation | 137K | +137K | 150 | 1.5B |
| 46 | BiRefNet_liteZhengPeng7 | Image Segmentation | 136.9K | +136.9K | 22 | 44.4M |
| 47 | POCKET-35B-GGUFFINAL-Bench | Text Generation | 136.6K | +136.6K | 82 | — |
| 48 | bloom-560mbigscience | Text Generation | 136.2K | +136.2K | 376 | 559M |
| 49 | gemma-4-E2B-it-qat-GGUFunsloth | Any to Any | 136.2K | +136.2K | 85 | — |
| 50 | Huihui-DeepSeek-V4-Flash-Vision-Exp-abliterated-GGUFhuihui-ai | Image Text to Text | 135.9K | +135.9K | 32 | — |