| 1 | Qwen3-4B-GGUFQwen | Text Generation | 343.9K | — | 150 | — |
| 2 | Qwen3.5-27B-GGUFunsloth | Image Text to Text | 343.8K | — | 503 | — |
| 3 | Qwen3.5-9B-FP8-dynamicRedHatAI | Image Text to Text | 343.8K | — | 7 | 9.4B |
| 4 | tiny-Glm4MoeForCausalLMtrl-internal-testing | Text Generation | 343.8K | — | 0 | 2.4M |
| 5 | Qwen3.6-35B-A3B-GGUFggml-org | Image Text to Text | 343.2K | — | 18 | — |
| 6 | DFN5B-CLIP-ViT-H-14-378apple | — | 342.5K | — | 110 | — |
| 7 | Gemmable-4-12B-MTP-GGUFMia-AiLab | — | 342.2K | — | 48 | — |
| 8 | bge-small-en-v1.5unsloth | Embeddings | 342.1K | — | 1 | 33.4M |
| 9 | Llama-4-Scout-17B-16E-Instructmeta-llama | Image Text to Text | 342.1K | — | 1,334 | 109B |
| 10 | Dolphin-Mistral-24B-Venice-Editiondphn | Text Generation | 341.5K | — | 656 | 24B |
| 11 | gemma-4-12B-it-FP8-DynamicRedHatAI | Any to Any | 341.4K | — | 5 | 13B |
| 12 | encodec_24khzfacebook | Embeddings | 341.1K | — | 55 | 23.3M |
| 13 | speaker-diarizationpyannote | Speech Recognition | 340.7K | — | 1,314 | — |
| 14 | marqo-fashionSigLIPMarqo | Zero-Shot Image Classification | 340.5K | — | 87 | 203M |
| 15 | Qwen1.5-MoE-A2.7BQwen | Text Generation | 340.3K | — | 228 | 14.3B |
| 16 | tiny-Gemma3ForConditionalGenerationtrl-internal-testing | Image Text to Text | 340.2K | — | 0 | 4.3M |
| 17 | whisper-large-v3-ggufhandy-computer | Speech Recognition | 339.3K | — | 1 | — |
| 18 | Conan-embedding-v1TencentBAC | — | 338.6K | — | 166 | 326M |
| 19 | Qwen3-VL-4B-Instruct-GGUFunsloth | Image Text to Text | 338.5K | — | 72 | — |
| 20 | seamless-m4t-v2-largefacebook | Speech Recognition | 338.2K | — | 1,009 | 2.3B |
| 21 | TimeMoE-50MMaple728 | Time Series Forecasting | 337.9K | — | 21 | 113M |
| 22 | qwen3.5-4b-reliquary-v4ReliquaryForge | — | 337.7K | — | 2 | 4B |
| 23 | VLM2Vec-FullTIGER-Lab | Text Generation | 337.5K | — | 29 | 4.1B |
| 24 | GLM-5.2-GGUFunsloth | Text Generation | 337.4K | — | 641 | — |
| 25 | opus-mt-de-enHelsinki-NLP | Translation | 336.3K | — | 50 | — |
| 26 | Qwen3-TTS-12Hz-1.7B-VoiceDesignQwen | Text to Speech | 336K | — | 394 | 1.9B |
| 27 | MinerU2.5-Pro-2604-1.2Bopendatalab | Image Text to Text | 335.5K | — | 165 | 1.2B |
| 28 | Qwen2.5-7B-Instruct-GGUFbartowski | Text Generation | 335.1K | — | 73 | — |
| 29 | SCAIL-2Comfy-Org | — | 334.7K | — | 108 | — |
| 30 | gemma-4-31B-it-qat-q4_0-ggufgoogle | Image Text to Text | 333.9K | — | 125 | — |
| 31 | TiRexNX-AI | Time Series Forecasting | 333.8K | — | 98 | — |
| 32 | tiny-NemotronHForCausalLM-nanotrl-internal-testing | Text Generation | 333.8K | — | 0 | 4.2M |
| 33 | Qwen3-8B-GGUFQwen | Text Generation | 333.7K | — | 251 | — |
| 34 | Parable-Qwen3-8B-Claude-Fable-5-GGUFAnkitAI | Text Generation | 333K | — | 1 | — |
| 35 | xflux_text_encodersXLabs-AI | Text Generation | 331.9K | — | 21 | 4.8B |
| 36 | olmOCR-2-7B-1025allenai | Image Text to Text | 331.3K | — | 157 | 8.3B |
| 37 | PP-LCNet_x1_0_doc_oriPaddlePaddle | Image to Text | 330.5K | — | 21 | — |
| 38 | NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4nvidia | Text Generation | 330.2K | — | 311 | 303B |
| 39 | VoxCPM2openbmb | Text to Speech | 330K | — | 1,544 | 2.3B |
| 40 | olmOCR-2-7B-1025-FP8allenai | Image Text to Text | 329.8K | — | 254 | 8.3B |
| 41 | Qwen3-4B-GGUFMaziyarPanahi | Text Generation | 329.6K | — | 8 | — |
| 42 | llmlingua-2-bert-base-multilingual-cased-meetingbankmicrosoft | Token Classification | 328.9K | — | 55 | 177M |
| 43 | wav2vec2-large-xlsr-53-sloveniananton-l | Speech Recognition | 328.7K | — | 0 | — |
| 44 | whisper-large-v3-turbo-ggufhandy-computer | Speech Recognition | 328.4K | — | 3 | — |
| 45 | wav2vec2-large-xlsr-knamoghsgopadi | Speech Recognition | 327.9K | — | 1 | — |
| 46 | T-lite-it-2.1t-tech | Text Generation | 327.9K | — | 26 | 8.2B |
| 47 | CodeRankEmbednomic-ai | — | 327.6K | — | 77 | 137M |
| 48 | grug-27b-ggufProCreations | — | 327.1K | — | 16 | — |
| 49 | llmdet_baseiSEE-Laboratory | Zero Shot Object Detection | 326.5K | — | 10 | 233M |
| 50 | ruri-v3-reranker-310mcl-nagoya | Text Ranking | 325.3K | — | 15 | 315M |