| 1 | docling-layout-herondocling-project | — | 1.8M | — | 53 | 42.9M |
| 2 | wav2vec2-large-xlsr-53-arabicjonatasgrosman | Speech Recognition | 1.8M | — | 54 | — |
| 3 | wav2vec2-base-960hfacebook | Speech Recognition | 1.8M | — | 401 | 94.4M |
| 4 | multi-qa-mpnet-base-dot-v1sentence-transformers | Sentence Similarity | 1.8M | — | 194 | 109M |
| 5 | deepseek-v4-ggufantirez | Text Generation | 1.8M | — | 459 | — |
| 6 | Meta-Llama-3-8B-Instructmeta-llama | Text Generation | 1.8M | — | 4,841 | 8B |
| 7 | parakeet-unified-en-0.6b-ggufhandy-computer | Speech Recognition | 1.7M | — | 4 | — |
| 8 | DeepSeek-V4-Flashdeepseek-ai | Text Generation | 1.7M | — | 2,133 | 291B |
| 9 | CLIP-convnext_base_w-laion2B-s13B-b82K-augreglaion | Zero-Shot Image Classification | 1.7M | — | 9 | — |
| 10 | siglip-so400m-patch14-384google | Zero-Shot Image Classification | 1.7M | — | 682 | 878M |
| 11 | mmarco-mMiniLMv2-L12-H384-v1cross-encoder | Text Ranking | 1.7M | — | 79 | 118M |
| 12 | paraphrase-MiniLM-L3-v2sentence-transformers | Sentence Similarity | 1.7M | — | 30 | 17.4M |
| 13 | Qwen3-8B-AWQQwen | Text Generation | 1.7M | — | 53 | 8.2B |
| 14 | Qwen3-Coder-Next-FP8Qwen | Text Generation | 1.7M | — | 173 | 79.7B |
| 15 | resnet18.a1_in1ktimm | Image Classification | 1.7M | — | 14 | 11.7M |
| 16 | wav2vec2-xls-r-300m-cs-250comodoro | Speech Recognition | 1.7M | — | 3 | 315M |
| 17 | Qwen3.5-122B-A10BQwen | Image Text to Text | 1.7M | — | 610 | 125B |
| 18 | nomic-embed-text-v2-moenomic-ai | Sentence Similarity | 1.7M | — | 495 | 475M |
| 19 | Qwen3-30B-A3B-Instruct-2507Qwen | Text Generation | 1.7M | — | 828 | 30.5B |
| 20 | Qwen2-VL-7B-Instruct-AWQQwen | Image Text to Text | 1.7M | — | 48 | 8.3B |
| 21 | Qwen3.8-27B-GGUFlmstudio-community | — | 1.7M | — | 29 | — |
| 22 | Kokoro-82M-v1.0-ONNXonnx-community | Text to Speech | 1.7M | — | 252 | — |
| 23 | Gemma-4-26B-A4B-NVFP4nvidia | Text Generation | 1.7M | — | 129 | 14.4B |
| 24 | flan-t5-basegoogle | — | 1.7M | — | 1,091 | 248M |
| 25 | parakeet-tdt-0.6b-v3mlx-community | Speech Recognition | 1.6M | — | 52 | 627M |
| 26 | Qwen3.6-35B-A3B-NVFP4RedHatAI | Image Text to Text | 1.6M | — | 172 | 34.7B |
| 27 | WanVideo_comfyKijai | — | 1.6M | — | 2,482 | — |
| 28 | gemma-4-31B-it-FP8-blockRedHatAI | Image Text to Text | 1.6M | — | 44 | 31.3B |
| 29 | GLM-5.2-FP8zai-org | Text Generation | 1.6M | — | 259 | 753B |
| 30 | resnet18.a3_in1ktimm | Image Classification | 1.6M | — | 0 | 11.7M |
| 31 | SmolLM2-135M-InstructHuggingFaceTB | Text Generation | 1.6M | — | 402 | 135M |
| 32 | Qwen3.5-2B-BaseQwen | Image Text to Text | 1.6M | — | 86 | 2.3B |
| 33 | bert-tinyprajjwal1 | — | 1.6M | — | 147 | — |
| 34 | TRELLIS.2-4Bmicrosoft | Image To 3d | 1.6M | — | 1,133 | — |
| 35 | faster-whisper-baseSystran | Speech Recognition | 1.6M | — | 34 | — |
| 36 | gemma-4-12B-it-qat-w4a16-ctgoogle | Any to Any | 1.6M | — | 56 | 13.3B |
| 37 | stable-diffusion-xl-base-1.0stabilityai | Text to Image | 1.6M | — | 8,067 | 2.6B |
| 38 | Qwen2-VL-7B-InstructQwen | Image Text to Text | 1.6M | — | 1,284 | 8.3B |
| 39 | phi-2microsoft | Text Generation | 1.6M | — | 3,500 | 2.8B |
| 40 | Llama-3.2-1Bmeta-llama | Text Generation | 1.6M | — | 2,543 | 1.2B |
| 41 | OTel-LLM-E4B-ITfarbodtavakkoli | Text Generation | 1.6M | — | 0 | — |
| 42 | gemma-4-31B-it-qat-w4a16-ctgoogle | Image Text to Text | 1.6M | — | 60 | 33.6B |
| 43 | LTX-2.3Lightricks | Image To Video | 1.6M | — | 1,831 | — |
| 44 | faster-whisper-tinySystran | Speech Recognition | 1.6M | — | 24 | — |
| 45 | romanian-wav2vec2gigant | Speech Recognition | 1.6M | — | 8 | 315M |
| 46 | fairface_age_image_detectiondima806 | Image Classification | 1.6M | — | 81 | 85.8M |
| 47 | gemma-3-270mgoogle | Text Generation | 1.6M | — | 1,075 | 268M |
| 48 | distilroberta-basedistilbert | Fill Mask | 1.5M | — | 179 | 82.8M |
| 49 | SapBERT-from-PubMedBERT-fulltextcambridgeltl | Embeddings | 1.5M | — | 77 | 109M |
| 50 | Depth-Anything-V2-Small-hfdepth-anything | Depth Estimation | 1.5M | — | 45 | 24.8M |