| 1 | all-MiniLM-L6-v2-onnxQdrant | Sentence Similarity | 225.5K | +225.5K | 14 | — |
| 2 | KAT-Coder-V2.5-Dev-APEX-GGUFmudler | — | 225.2K | +225.2K | 62 | — |
| 3 | vae-text-encorder-for-flux-klein-9bComfy-Org | — | 224.5K | +224.5K | 213 | — |
| 4 | GLM-5.2zai-org | Text Generation | 224K | +224K | 5,142 | 753B |
| 5 | Qwen3.6-35B-A3B-Uncensored-HauhauCS-AggressiveHauhauCS | Image Text to Text | 223.8K | +223.8K | 3,809 | — |
| 6 | DeepSeek-V4.1-Flashdeepseek-ai | Image Text to Text | 223.7K | +223.7K | 4,006 | 763B |
| 7 | jina-reranker-v2-base-multilingualjinaai | Text Ranking | 223.7K | +223.7K | 355 | 278M |
| 8 | llama-3.3-70b-instruct-awqcasperhansen | Text Generation | 222K | +222K | 46 | 70.6B |
| 9 | snowflake-arctic-embed-l-v2.0Snowflake | Sentence Similarity | 221.7K | +221.7K | 253 | 568M |
| 10 | pubmedbert-base-embeddingsNeuML | Sentence Similarity | 221.3K | +221.3K | 198 | 109M |
| 11 | privacy-filter-nemotron-GGUFLocalAI-io | Token Classification | 220.5K | +220.5K | 1 | — |
| 12 | w2v-xls-r-ukYehor | Speech Recognition | 220.1K | +220.1K | 8 | 315M |
| 13 | Qwen3.6-27B-AWQ-INT4cyankiwi | Image Text to Text | 219.9K | +219.9K | 111 | 29.3B |
| 14 | Apertus-v1.5-8Bswiss-ai | Image Text to Text | 219.3K | +219.3K | 120 | 8.9B |
| 15 | gemma-4-26B-A4B-it-FP8-dynamicRedHatAI | Image Text to Text | 218K | +218K | 41 | 26.5B |
| 16 | jina-reranker-v3jinaai | Text Ranking | 218K | +218K | 146 | 597M |
| 17 | dreamshaper-7Lykon | Text to Image | 217.5K | +217.5K | 66 | 860M |
| 18 | whisper-tiny.enXenova | Speech Recognition | 217.3K | +217.3K | 27 | — |
| 19 | LLaDA-8B-InstructGSAI-ML | Text Generation | 217.1K | +217.1K | 364 | 8B |
| 20 | bloomz-560mbigscience | Text Generation | 217K | +217K | 138 | 559M |
| 21 | Qwen3-VLComfy-Org | — | 216.6K | +216.6K | 82 | — |
| 22 | Gemma4-12B-QAT-Uncensored-HauhauCS-BalancedHauhauCS | Image Text to Text | 215K | +215K | 393 | — |
| 23 | vit-base-nsfw-detectorAdamCodd | Image Classification | 214.9K | +214.9K | 84 | 86.1M |
| 24 | faster-whisper-mediumSystran | Speech Recognition | 214.1K | +214.1K | 69 | — |
| 25 | Qwen2.5-Coder-32B-Instruct-AWQQwen | Text Generation | 213.9K | +213.9K | 41 | 32.8B |
| 26 | opus-mt-ru-enHelsinki-NLP | Translation | 213.6K | +213.6K | 102 | — |
| 27 | umberto-commoncrawl-cased-v1Musixmatch | Fill Mask | 212.9K | +212.9K | 19 | — |
| 28 | CLIP-ViT-B-16-laion2B-s34B-b88Klaion | Zero-Shot Image Classification | 212.9K | +212.9K | 39 | — |
| 29 | F5-TTSSWivid | Text to Speech | 212.5K | +212.5K | 1,212 | — |
| 30 | Qwen3.6-35B-A3B-NVFP4unsloth | Image Text to Text | 211.4K | +211.4K | 121 | 24.6B |
| 31 | stable-diffusion-safety-checkerCompVis | — | 211.2K | +211.2K | 141 | — |
| 32 | bge-reranker-v2.5-gemma2-lightweight-gptqboboliu | Text Generation | 211K | +211K | 0 | 9.2B |
| 33 | faster-whisper-large-v3Systran | Speech Recognition | 210.6K | +210.6K | 678 | — |
| 34 | answerai-colbert-small-v1answerdotai | — | 210.6K | +210.6K | 163 | 33.4M |
| 35 | DeepSeek-R1deepseek-ai | Text Generation | 210.4K | +210.4K | 14.3K | 684B |
| 36 | Llama-2-7b-hfmeta-llama | Text Generation | 210.2K | +210.2K | 2,436 | 6.7B |
| 37 | GigaAM-v3ai-sage | Speech Recognition | 208.8K | +208.8K | 170 | — |
| 38 | mDeBERTa-v3-base-xnli-multilingual-nli-2mil7MoritzLaurer | Zero-Shot Classification | 208.7K | +208.7K | 393 | 279M |
| 39 | gemma-3-12b-it-4bitmlx-community | Image Text to Text | 208.7K | +208.7K | 6 | — |
| 40 | opus-mt-nl-enHelsinki-NLP | Translation | 208K | +208K | 10 | — |
| 41 | longformer-base-4096allenai | — | 207.8K | +207.8K | 229 | — |
| 42 | chronos-t5-tinyamazon | Time Series Forecasting | 207.4K | +207.4K | 121 | 8.4M |
| 43 | bge-base-zh-v1.5BAAI | Embeddings | 206.8K | +206.8K | 110 | — |
| 44 | multi-qa-MiniLM-L6-cos-v1sentence-transformers | Sentence Similarity | 206.3K | +206.3K | 138 | 22.7M |
| 45 | bert-tinyprajjwal1 | — | 206.2K | +206.2K | 148 | — |
| 46 | wavlm-largemicrosoft | Embeddings | 205.8K | +205.8K | 114 | — |
| 47 | SmolLM2-360MHuggingFaceTB | Text Generation | 204.7K | +204.7K | 136 | 362M |
| 48 | Qwen3.6-35B-A3B-abliterated-v4Bahushruth | Text Generation | 204.6K | +204.6K | 11 | 34.7B |
| 49 | Qwen3-Coder-480B-A35B-Instruct-FP8Qwen | Text Generation | 204.4K | +204.4K | 161 | 480B |
| 50 | wav2vec2-xlsr-nepaligagan3012 | Speech Recognition | 204.4K | +204.4K | 8 | — |