| 1 | layoutlmv3-basemicrosoft | — | 1.1M | — | 508 | 125M |
| 2 | DeepSeek-R1-0528-Qwen3-8Bdeepseek-ai | Text Generation | 1.1M | — | 1,083 | 8.2B |
| 3 | Huihui-Qwen3.8-27B-abliterated-GGUFhuihui-ai | Image Text to Text | 1.1M | — | 318 | — |
| 4 | ms-marco-MiniLM-L2-v2cross-encoder | Text Ranking | 1.1M | — | 14 | 15.6M |
| 5 | bge-small-enBAAI | Embeddings | 1.1M | — | 94 | 33.4M |
| 6 | vit_small_patch14_dinov2.lvd142mtimm | Image Feature Extraction | 1.1M | — | 8 | 22.1M |
| 7 | Qwen2.5-VL-7B-Instruct-AWQQwen | Image Text to Text | 1.1M | — | 105 | 8.3B |
| 8 | Qwen3-4B-BaseQwen | Text Generation | 1.1M | — | 96 | 4B |
| 9 | ko-sroberta-multitaskjhgan | Sentence Similarity | 1.1M | — | 150 | 111M |
| 10 | chronos-t5-baseamazon | Time Series Forecasting | 1.1M | — | 45 | 201M |
| 11 | opus-mt-nl-enHelsinki-NLP | Translation | 1.1M | — | 10 | — |
| 12 | Unlimited-OCR-AWQsahilchachra | Image Text to Text | 1.1M | — | 1 | 3.4B |
| 13 | vakyansh-wav2vec2-tamil-tam-250Harveenchadha | Speech Recognition | 1.1M | — | 4 | — |
| 14 | gemma-3-12b-itgoogle | Image Text to Text | 1.1M | — | 810 | 12.2B |
| 15 | Qwen3.6-35B-A3B-abliterated-v4Bahushruth | Text Generation | 1.1M | — | 8 | 34.7B |
| 16 | vae-text-encorder-for-flux-klein-9bComfy-Org | — | 1.1M | — | 189 | — |
| 17 | bm25Qdrant | Sentence Similarity | 1.1M | — | 35 | — |
| 18 | Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V10-GGUFLuffyTheFox | Image Text to Text | 1.1M | — | 545 | — |
| 19 | Qwen3.6-27B-Text-NVFP4-MTPsakamakismile | Text Generation | 1.1M | — | 81 | 16.7B |
| 20 | grounding-dino-tinyIDEA-Research | Zero Shot Object Detection | 1.1M | — | 114 | 172M |
| 21 | wav2vec2-xls-r-300m-mixedmesolitica | Speech Recognition | 1.1M | — | 5 | — |
| 22 | bge-micro-v2TaylorAI | Sentence Similarity | 1.1M | — | 65 | 17.4M |
| 23 | wav2vec2-xls-r-300m-hebrewimvladikon | Speech Recognition | 1.1M | — | 6 | 315M |
| 24 | Llama-3.2-3B-Instructmeta-llama | Text Generation | 1.1M | — | 2,450 | 3.2B |
| 25 | gemma-4-12B-it-qat-GGUFunsloth | Any to Any | 1.1M | — | 440 | — |
| 26 | LTX2.3_comfyKijai | — | 1.1M | — | 593 | — |
| 27 | jina-embeddings-v2-small-enjinaai | Embeddings | 1.1M | — | 142 | 32.7M |
| 28 | sdxl-turbostabilityai | Text to Image | 1M | — | 2,623 | 2.6B |
| 29 | MiniCPM-o-4_5openbmb | Any to Any | 1M | — | 1,473 | 9.4B |
| 30 | stable-diffusion-safety-checkerCompVis | — | 1M | — | 141 | — |
| 31 | DeepSeek-V3-0324deepseek-ai | Text Generation | 1M | — | 3,161 | 685B |
| 32 | ced-ggufmudler | Audio Classification | 1M | — | 2 | — |
| 33 | gemma-4-E2B-it-litert-lmlitert-community | — | 1M | — | 408 | — |
| 34 | gte-large-en-v1.5Alibaba-NLP | Sentence Similarity | 1M | — | 239 | 434M |
| 35 | Qwen3.6-27B-GGUFunsloth | Image Text to Text | 1M | — | 947 | — |
| 36 | DeepSeek-V4-Prodeepseek-ai | Text Generation | 1M | — | 5,476 | 1.6T |
| 37 | ltx-2Comfy-Org | — | 1M | — | 147 | — |
| 38 | distiluse-base-multilingual-cased-v1sentence-transformers | Sentence Similarity | 1M | — | 133 | 135M |
| 39 | wav2vec2-base-vi-vlsp2020nguyenvulebinh | Speech Recognition | 1M | — | 2 | — |
| 40 | nemotron-3.5-asr-streaming-0.6bnvidia | Speech Recognition | 1M | — | 1,058 | 638M |
| 41 | MiniCPM5-1Bopenbmb | Text Generation | 1M | — | 1,080 | 1.1B |
| 42 | Qwen3-0.6B-BaseQwen | Text Generation | 1M | — | 186 | 596M |
| 43 | Qwen3.6-27B-MTP-GGUFunsloth | Image Text to Text | 1M | — | 1,306 | — |
| 44 | Qwen2.5-Omni-3BQwen | Any to Any | 1M | — | 346 | 5.5B |
| 45 | dinov3-vitl16-pretrain-lvd1689mcamenduru | Image Feature Extraction | 1M | — | 16 | 303M |
| 46 | SmolLM-1.7B-Instruct-quantized.w4a16nm-testing | Text Generation | 1M | — | 0 | 1.8B |
| 47 | gte-smallthenlper | Sentence Similarity | 1M | — | 189 | 33.4M |
| 48 | wav2vec2-large-xlsr-koreankresnik | Speech Recognition | 1M | — | 56 | 317M |
| 49 | twitter-xlm-roberta-base-sentimentcardiffnlp | Text Classification | 994.9K | — | 275 | — |
| 50 | efficientnet_b0.ra_in1ktimm | Image Classification | 991.9K | — | 10 | 5.3M |