| 1 | Qwen3.6-27B-Uncensored-HauhauCS-BalancedHauhauCS | Image Text to Text | 393.8K | — | 205 | — |
| 2 | xlm-roberta-base-ner-hrlDavlan | Token Classification | 393.7K | — | 28 | 277M |
| 3 | NVIDIA-Nemotron-Nano-9B-v2nvidia | Text Generation | 393.2K | — | 514 | 8.9B |
| 4 | mDeBERTa-v3-base-mnli-xnliMoritzLaurer | Zero-Shot Classification | 393K | — | 314 | 279M |
| 5 | gemma-4-12B-it-qat-q4_0-unquantizedgoogle | Any to Any | 392.1K | — | 76 | 12B |
| 6 | gliner2-large-v1fastino | — | 391.1K | — | 94 | 486M |
| 7 | Qwen3-VL-30B-A3B-InstructQwen | Image Text to Text | 390K | — | 593 | 31.1B |
| 8 | Qwen2.5-72B-InstructQwen | Text Generation | 388.9K | — | 976 | 72.7B |
| 9 | DeepSeek-V4-Flash-0731-GGUFunsloth | — | 388.3K | — | 724 | — |
| 10 | flux1-devComfy-Org | — | 388.3K | — | 655 | — |
| 11 | Qwen3-30B-A3B-GPTQ-Int4Qwen | Text Generation | 387.8K | — | 55 | 30.5B |
| 12 | Qwen3-30B-A3B-GGUFQwen | Text Generation | 387.8K | — | 77 | — |
| 13 | koelectra-emotion-v1circulus | — | 387.7K | — | 0 | — |
| 14 | Kimi-VL-A3B-Instructmoonshotai | Image Text to Text | 387.4K | — | 280 | 16.4B |
| 15 | m2m100_418Mfacebook | — | 387K | — | 344 | — |
| 16 | multilingual-e5-large-onnxQdrant | Sentence Similarity | 386.9K | — | 4 | — |
| 17 | segformer_b2_clothesmattmdjaga | Image Segmentation | 386.6K | — | 506 | 27.4M |
| 18 | ACE-Step-1.5-GGUFServeurperso | — | 386.5K | — | 89 | — |
| 19 | LTX-2Lightricks | Image To Video | 384.3K | — | 1,776 | 18.9B |
| 20 | sam-vit-hugefacebook | Mask Generation | 381K | — | 197 | 641M |
| 21 | Rex-Omni-AWQIDEA-Research | — | 380.5K | — | 4 | 3.8B |
| 22 | whisper-mediumopenai | Speech Recognition | 380.1K | — | 296 | 764M |
| 23 | vit_large_patch14_reg4_dinov2.lvd142mtimm | Image Feature Extraction | 380.1K | — | 7 | 304M |
| 24 | gemma-4-12B-it-MLX-4bitlmstudio-community | Any to Any | 380.1K | — | 3 | 1.9B |
| 25 | Qwen3-4B-Thinking-2507Qwen | Text Generation | 379.7K | — | 610 | 4B |
| 26 | ESMFold2biohub | — | 378.6K | — | 52 | 235M |
| 27 | wav2vec2-xls-r-300m-sk-cv8comodoro | Speech Recognition | 378.5K | — | 0 | — |
| 28 | typhoon-ocr-3btyphoon-ai | Image Text to Text | 378.4K | — | 9 | 3.8B |
| 29 | mistral-7b-v0.3-bnb-4bitunsloth | Text Generation | 375.8K | — | 23 | 7.5B |
| 30 | VieNeu-TTS-v3-Turbopnnbao-ump | Text to Speech | 375.4K | — | 52 | 131M |
| 31 | Kronos-miniNeoQuasar | Time Series Forecasting | 375.2K | — | 31 | 4.1M |
| 32 | e5-mistral-7b-instruct-bnb-4bitgabor-hosu | Embeddings | 375K | — | 0 | 7.3B |
| 33 | DFN2B-CLIP-ViT-B-16apple | — | 374.5K | — | 13 | — |
| 34 | bge-small-en-v1.5-GGUFunsloth | Embeddings | 374.2K | — | 2 | — |
| 35 | indic-parler-ttsai4bharat | Text to Speech | 373.8K | — | 302 | 938M |
| 36 | USER-bge-m3deepvk | Sentence Similarity | 372.6K | — | 83 | 359M |
| 37 | Ministral-3-3B-Instruct-2512mistralai | — | 372.6K | — | 275 | 3.8B |
| 38 | mask2former-swin-large-ade-semanticfacebook | Image Segmentation | 371.8K | — | 24 | 216M |
| 39 | gemma-4-E4B-it-uncensored-hereticllmfan46 | Any to Any | 371.4K | — | 6 | 8B |
| 40 | Phi-4-multimodal-instructmicrosoft | Speech Recognition | 371K | — | 1,613 | 5.6B |
| 41 | bge-small-en-v1.5Xenova | Embeddings | 370.6K | — | 20 | — |
| 42 | gemma-4-12B-it-MLX-8bitlmstudio-community | Any to Any | 370.6K | — | 3 | 3.4B |
| 43 | dinov2-giantfacebook | Image Feature Extraction | 370.6K | — | 63 | 1.1B |
| 44 | SmolLM3-3B-BaseHuggingFaceTB | Text Generation | 370.4K | — | 170 | 3.1B |
| 45 | GTE-ModernColBERT-v1lightonai | Sentence Similarity | 368.8K | — | 175 | 149M |
| 46 | Parable-Qwen3-4B-Claude-Fable-5-GGUFAnkitAI | Text Generation | 367.9K | — | 14 | — |
| 47 | snowflake-arctic-embed-xsSnowflake | Sentence Similarity | 367.6K | — | 43 | 22.6M |
| 48 | DeepSeek-V4-Flash-0731-NVFP4MJPansa | Text Generation | 367.2K | — | 15 | 304B |
| 49 | gemma4-e4b-claims-comparisonk-chirkunov | Text Generation | 366.9K | — | 0 | 7.9B |
| 50 | gemma-4-12B-it-MLX-6bitlmstudio-community | Any to Any | 366.8K | — | 2 | 2.6B |