| 1 | Llama-3.2-1B-Instructmeta-llama | Text Generation | 1,583 | — | 1,583 | 1.2B |
| 2 | Solidity-LLMChain-GPT | Text Generation | 1,579 | — | 1,579 | 2.8B |
| 3 | stable-audio-open-1.0stabilityai | Text to Audio | 1,565 | — | 1,565 | 1.2B |
| 4 | DeepSeek-R1-Distill-Qwen-1.5Bdeepseek-ai | Text Generation | 1,565 | — | 1,565 | 1.8B |
| 5 | barksuno | Text to Speech | 1,557 | — | 1,557 | — |
| 6 | Qwen3.6-35B-A3B-GGUFunsloth | Image Text to Text | 1,556 | — | 1,556 | — |
| 7 | GOT-OCR2_0stepfun-ai | Image Text to Text | 1,554 | — | 1,554 | 716M |
| 8 | Qwen2.5-7B-InstructQwen | Text Generation | 1,553 | — | 1,553 | 7.6B |
| 9 | Qwen3.5-397B-A17BQwen | Image Text to Text | 1,552 | — | 1,552 | 403B |
| 10 | whisper.cppggerganov | Speech Recognition | 1,550 | — | 1,550 | — |
| 11 | Wan2.1-T2V-14BWan-AI | Text to Video | 1,549 | — | 1,549 | 14.3B |
| 12 | segmentation-3.0pyannote | Voice Activity Detection | 1,543 | — | 1,543 | — |
| 13 | VoxCPM2openbmb | Text to Speech | 1,542 | — | 1,542 | 2.3B |
| 14 | parakeet-tdt-0.6b-v2nvidia | Speech Recognition | 1,536 | — | 1,536 | — |
| 15 | Qwen3-0.6BQwen | Text Generation | 1,533 | — | 1,533 | 752M |
| 16 | gpt-j-6bEleutherAI | Text Generation | 1,526 | — | 1,526 | — |
| 17 | Meta-Llama-3-70B-Instructmeta-llama | Text Generation | 1,523 | — | 1,523 | 70.6B |
| 18 | Qwen-Image-Edit-2511-Multiple-Angles-LoRAfal | Image To Image | 1,514 | — | 1,514 | — |
| 19 | MiniMax-H3Comfy-Org | — | 1,511 | — | 1,511 | — |
| 20 | MiniMax-M2.5MiniMaxAI | Text Generation | 1,506 | — | 1,506 | 229B |
| 21 | MiniMax-M2MiniMaxAI | Text Generation | 1,503 | — | 1,503 | 229B |
| 22 | gemma-4-E4B-itgoogle | Any to Any | 1,499 | — | 1,499 | 8B |
| 23 | gemma-3n-E4B-it-litert-previewgoogle | Image Text to Text | 1,495 | — | 1,495 | — |
| 24 | MiniMax-M3MiniMaxAI | Image Text to Text | 1,494 | — | 1,494 | 427B |
| 25 | bitnet-b1.58-2B-4Tmicrosoft | Text Generation | 1,492 | — | 1,492 | 850M |
| 26 | Qwen3.5-35B-A3BQwen | Image Text to Text | 1,491 | — | 1,491 | 36B |
| 27 | blip-image-captioning-largeSalesforce | Image to Text | 1,486 | — | 1,486 | 470M |
| 28 | gemma-4-12B-itgoogle | Any to Any | 1,483 | — | 1,483 | 12B |
| 29 | gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUFyuxinlu1 | Text Generation | 1,478 | — | 1,478 | — |
| 30 | Qwen3.5-35B-A3B-Uncensored-HauhauCS-AggressiveHauhauCS | Image Text to Text | 1,477 | — | 1,477 | — |
| 31 | MiniCPM-o-4_5openbmb | Any to Any | 1,473 | — | 1,473 | 9.4B |
| 32 | DeepSeek-V3.2deepseek-ai | Text Generation | 1,469 | — | 1,469 | 685B |
| 33 | gemma-3-4b-itgoogle | Image Text to Text | 1,461 | — | 1,461 | 4.3B |
| 34 | bert-base-chinesegoogle-bert | Fill Mask | 1,459 | — | 1,459 | 103M |
| 35 | control_v1p_sd15_qrcode_monstermonster-labs | — | 1,457 | — | 1,457 | 361M |
| 36 | gemma-2-2b-itgoogle | Text Generation | 1,456 | — | 1,456 | 2.6B |
| 37 | Phi-3-mini-4k-instructmicrosoft | Text Generation | 1,453 | — | 1,453 | 3.8B |
| 38 | OpenELMapple | — | 1,452 | — | 1,452 | — |
| 39 | ControlNet-modules-safetensorswebui | — | 1,441 | — | 1,441 | — |
| 40 | moondream2vikhyatk | Image Text to Text | 1,432 | — | 1,432 | 1.9B |
| 41 | gemma-4-26B-A4B-itgoogle | Image Text to Text | 1,428 | — | 1,428 | 25.8B |
| 42 | Qwen-Fixed-Chat-Templatesfroggeric | — | 1,427 | — | 1,427 | — |
| 43 | sd-vae-ft-mse-originalstabilityai | Text to Image | 1,421 | — | 1,421 | — |
| 44 | stable-diffusion-xl-base-0.9stabilityai | Text to Image | 1,419 | — | 1,419 | 2.6B |
| 45 | MiniCPM-Llama3-V-2_5openbmb | Image Text to Text | 1,413 | — | 1,413 | 8.5B |
| 46 | GLM-4.5zai-org | Text Generation | 1,410 | — | 1,410 | 358B |
| 47 | FLUX.1-dev-ggufcity96 | Text to Image | 1,406 | — | 1,406 | — |
| 48 | IP-Adapterh94 | Text to Image | 1,397 | — | 1,397 | — |
| 49 | flux_text_encoderscomfyanonymous | — | 1,397 | — | 1,397 | — |
| 50 | Mistral-Small-3.1-24B-Instruct-2503mistralai | — | 1,377 | — | 1,377 | 24B |