| 1 | VibeVoice-Realtime-0.5Bmicrosoft | Text to Speech | 639.1K | — | 1,278 | 1B |
| 2 | mt5-smallgoogle | — | 637.8K | — | 191 | — |
| 3 | tiny-random-Gemma2ForCausalLMhmellor | Text Generation | 637.8K | — | 0 | 8.4M |
| 4 | MiniMax-M2.5MiniMaxAI | Text Generation | 637.3K | — | 1,507 | 229B |
| 5 | unifiedqa-t5-smallallenai | — | 636.5K | — | 5 | — |
| 6 | zerank-2-rerankerzeroentropy | Text Ranking | 635.6K | — | 116 | 4B |
| 7 | Apertus-8B-Instruct-2509swiss-ai | Text Generation | 635.1K | — | 487 | 8.1B |
| 8 | Qwen3.6-27B-MLX-6bitlmstudio-community | Image Text to Text | 635.1K | — | 2 | 6.3B |
| 9 | gemma-4-E4B-it-GGUFlmstudio-community | — | 634.6K | — | 64 | — |
| 10 | MiniMax-M2.5-NVFP4nvidia | Text Generation | 634K | — | 37 | 116B |
| 11 | Qwen3.6-27B-MLX-5bitlmstudio-community | Image Text to Text | 633.3K | — | 0 | 5.5B |
| 12 | Qwen3-32B-AWQQwen | Text Generation | 631.5K | — | 139 | 32.8B |
| 13 | DeepSeek-R1-Distill-Qwen-32Bdeepseek-ai | Text Generation | 631.4K | — | 1,599 | 32.8B |
| 14 | Phi-3-mini-4k-instructmicrosoft | Text Generation | 630.2K | — | 1,453 | 3.8B |
| 15 | prokbert-mini-promoterneuralbioinfo | Text Classification | 630K | — | 0 | 20.6M |
| 16 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4nvidia | Text Generation | 629.6K | — | 356 | 17.8B |
| 17 | Cosmos-Reason2-8Bnvidia | Image Text to Text | 627.7K | — | 213 | 8.8B |
| 18 | privacy-filter-nemotron-GGUFLocalAI-io | Token Classification | 626K | — | 0 | — |
| 19 | turn-detectorlivekit | Text Classification | 622.7K | — | 139 | 135M |
| 20 | qwen3-4b-base-dapo-v4ReliquaryForge | — | 620.9K | — | 1 | 4B |
| 21 | tiny-Qwen3MoeForCausalLMtrl-internal-testing | Text Generation | 620.8K | — | 1 | 2.6M |
| 22 | Ornith-1.0-35B-FP8protoLabsAI | Text Generation | 618.6K | — | 8 | 35.1B |
| 23 | gemma-4-31B-it-assistantgoogle | Any to Any | 618.3K | — | 320 | 470M |
| 24 | wav2vec2-large-xlsr-mvc-swahilieddiegulay | Speech Recognition | 617K | — | 3 | 315M |
| 25 | MiniMax-H3-Turbo-Loralarryvrh | Text to Video | 613.9K | — | 853 | — |
| 26 | bert-portuguese-nerlfcc | Token Classification | 611.5K | — | 9 | — |
| 27 | DeepSeek-Coder-V2-Lite-Instructdeepseek-ai | Text Generation | 611.4K | — | 641 | 15.7B |
| 28 | wav2vec2-large-xlsr-catalasoftcatala | Speech Recognition | 610.9K | — | 1 | — |
| 29 | higgs-tts-2-3b-basebosonai | Text to Speech | 609.2K | — | 693 | 5.8B |
| 30 | Qwen3.8-27B-GGUFggml-org | Image Text to Text | 608.7K | — | 53 | — |
| 31 | e5-mistral-7b-instructintfloat | Embeddings | 605.1K | — | 569 | 7.1B |
| 32 | Qwen2.5-Coder-7B-Instruct-AWQOrion-zhen | Text Generation | 603.3K | — | 1 | 7.6B |
| 33 | h2ovl-mississippi-800mh2oai | Text Generation | 602.5K | — | 40 | 826M |
| 34 | Qwen3.5-9B-MLX-4bitlmstudio-community | Image Text to Text | 602.3K | — | 4 | 1.9B |
| 35 | dinov3-vitb16-pretrain-lvd1689mfacebook | Image Feature Extraction | 600.4K | — | 228 | 85.7M |
| 36 | opus-mt-en-ruHelsinki-NLP | Translation | 599.2K | — | 99 | — |
| 37 | Qwen2.5-3B-Instruct-AWQQwen | Text Generation | 598.8K | — | 16 | 3.4B |
| 38 | HunyuanOCRtencent | Image Text to Text | 595.7K | — | 800 | 1.1B |
| 39 | Qwen2.5-Coder-7BQwen | Text Generation | 595.3K | — | 162 | 7.6B |
| 40 | bert-large-uncasedgoogle-bert | Fill Mask | 591.3K | — | 148 | 336M |
| 41 | boltzgen-1boltzgen | — | 590.5K | — | 5 | — |
| 42 | Llama-3.3-70B-Instruct-NVFP4nvidia | — | 590.3K | — | 50 | 40.6B |
| 43 | dino-vitb16facebook | Image Feature Extraction | 588.3K | — | 112 | — |
| 44 | conv-bert-baseYituTech | Embeddings | 587.9K | — | 10 | — |
| 45 | h2ovl-mississippi-2bh2oai | Text Generation | 587.6K | — | 43 | 2.2B |
| 46 | fnet-basegoogle | — | 587.2K | — | 18 | — |
| 47 | DeepSeek-R1-Distill-Qwen-1.5Bdeepseek-ai | Text Generation | 586.7K | — | 1,565 | 1.8B |
| 48 | gemma-4-26B-A4B-it-qat-GGUFunsloth | Image Text to Text | 586.6K | — | 387 | — |
| 49 | Qwen2.5-7BQwen | Text Generation | 585.7K | — | 306 | 7.6B |
| 50 | gemma-4-26B-A4B-it-QAT-MLX-4bitlmstudio-community | Image Text to Text | 585K | — | 15 | 4.6B |