Snapshot 2026-10-21. Likes measure Hub popularity, not quality. Datasets · Methodology.
| Rank | Model | Likes | Task |
|---|---|---|---|
| 1 | Qwen/Qwen3.8-27B | 18,126 | image-text-to-text |
| 2 | black-forest-labs/FLUX.1-dev | 15,690 | text-to-image |
| 3 | deepseek-ai/DeepSeek-R1 | 14,399 | text-generation |
| 4 | moonshotai/Kimi-K3 | 11,787 | image-text-to-text |
| 5 | Lightricks/LTX-2.5 | 8,727 | image-to-video |
| 6 | meta-llama/Llama-3.1-8B-Instruct | 8,536 | text-generation |
| 7 | stabilityai/stable-diffusion-xl-base-1.0 | 8,369 | text-to-image |
| 8 | hexgrad/Kokoro-82M | 7,247 | text-to-speech |
| 9 | CompVis/stable-diffusion-v1-4 | 7,134 | text-to-image |
| 10 | meta-llama/Meta-Llama-3-8B | 6,762 | text-generation |
| 11 | openai/whisper-large-v3 | 6,677 | automatic-speech-recognition |
| 12 | black-forest-labs/FLUX.1-schnell | 6,385 | text-to-image |
| 13 | Qwen/Qwen3.8-Flash-Next | 6,383 | image-text-to-text |
| 14 | MiniMaxAI/MiniMax-H3 | 6,268 | image-text-to-video |
| 15 | sentence-transformers/all-MiniLM-L6-v2 | 5,981 | sentence-similarity |
| 16 | convaiinnovations/laya | 5,758 | text-classification |
| 17 | deepseek-ai/DeepSeek-V4-Pro | 5,669 | text-generation |
| 18 | Tongyi-MAI/Z-Image-Turbo | 5,496 | text-to-image |
| 19 | meta-llama/Meta-Llama-3-8B-Instruct | 5,470 | text-generation |
| 20 | openai/gpt-oss-120b | 5,427 | text-generation |
| 21 | unsloth/Qwen3.8-27B-GGUF | 5,245 | — |
| 22 | openai/gpt-oss-20b | 5,197 | text-generation |
| 23 | zai-org/GLM-5.2 | 5,180 | text-generation |
| 24 | bigscience/bloom | 5,087 | text-generation |
| 25 | stabilityai/stable-diffusion-3-medium | 5,059 | text-to-image |
| 26 | meta-llama/Llama-2-7b-chat-hf | 4,911 | text-generation |
| 27 | baidu/Unlimited-OCR | 4,852 | image-text-to-text |
| 28 | facebook/sam3 | 4,836 | mask-generation |
| 29 | mistralai/Mixtral-8x7B-Instruct-v0.1 | 4,772 | — |
| 30 | deepseek-ai/DeepSeek-V4.1-Flash | 4,689 | image-text-to-text |
| 31 | meta-llama/Llama-2-7b | 4,574 | text-generation |
| 32 | pyannote/speaker-diarization-3.1 | 4,518 | automatic-speech-recognition |
| 33 | deepseek-ai/DeepSeek-V3 | 4,447 | text-generation |
| 34 | mistralai/Mistral-7B-v0.1 | 4,223 | text-generation |
| 35 | google/gemma-4-31B-it | 4,167 | image-text-to-text |
| 36 | lllyasviel/ControlNet-v1-1 | 4,158 | — |
| 37 | stabilityai/stable-diffusion-3.5-large | 4,146 | text-to-image |
| 38 | deepseek-ai/DeepSeek-V4-Flash-0731 | 4,083 | text-generation |
| 39 | WarriorMama777/OrangeMixs | 3,969 | text-to-image |
| 40 | BAAI/bge-m3 | 3,909 | sentence-similarity |
| 41 | coqui/XTTS-v2 | 3,902 | text-to-speech |
| 42 | lllyasviel/ControlNet | 3,886 | — |
| 43 | openai-community/gpt2 | 3,884 | text-generation |
| 44 | mistralai/Mistral-7B-Instruct-v0.3 | 3,806 | — |
| 45 | deepseek-ai/Janus-Pro-7B | 3,716 | any-to-any |
| 46 | microsoft/phi-2 | 3,528 | text-generation |
| 47 | openai/whisper-large-v3-turbo | 3,467 | automatic-speech-recognition |
| 48 | stabilityai/stable-video-diffusion-img2vid-xt | 3,463 | image-to-video |
| 49 | google/gemma-7b | 3,458 | text-generation |
| 50 | deepseek-ai/DeepSeek-OCR | 3,450 | image-text-to-text |
| 51 | Qwen/Qwen-Image-2.1 | 3,405 | text-to-image |
| 52 | prompthero/openjourney | 3,272 | text-to-image |
| 53 | mistralai/Mistral-7B-Instruct-v0.2 | 3,267 | text-generation |
| 54 | deepseek-ai/DeepSeek-V3-0324 | 3,220 | text-generation |
| 55 | pyannote/speaker-diarization-community-1 | 3,206 | automatic-speech-recognition |
| 56 | meta-llama/Llama-3.3-70B-Instruct | 3,149 | text-generation |
| 57 | nvidia/LocateAnything-3B | 3,125 | image-text-to-text |
| 58 | google-bert/bert-base-uncased | 3,043 | fill-mask |
| 59 | TaichuAI/ZDTaichu5.0-9B | 3,031 | image-text-to-text |
| 60 | Qwen/Qwen3.6-35B-A3B | 3,016 | image-text-to-text |
| 61 | moonshotai/Kimi-K2-Instruct | 3,004 | text-generation |
| 62 | bigcode/starcoder | 2,986 | text-generation |
| 63 | Qwen/QwQ-32B | 2,969 | text-generation |
| 64 | Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled | 2,964 | image-text-to-text |
| 65 | yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF | 2,964 | text-generation |
| 66 | nari-labs/Dia-1.6B | 2,931 | text-to-speech |
| 67 | zai-org/chatglm-6b | 2,926 | — |
| 68 | black-forest-labs/FLUX.1-Kontext-dev | 2,912 | image-to-image |
| 69 | zai-org/GLM-5.3-Flash | 2,910 | image-text-to-text |
| 70 | CompVis/stable-diffusion-v-1-4-original | 2,891 | text-to-image |
| 71 | moonshotai/Kimi-K2.5 | 2,890 | image-text-to-text |
| 72 | nvidia/personaplex-7b-v1 | 2,862 | audio-to-audio |
| 73 | meta-llama/Llama-3.2-3B-Instruct | 2,845 | text-generation |
| 74 | google/embeddinggemma-2 | 2,799 | feature-extraction |
| 75 | prism-ml/Ternary-Bonsai-2-27B-gguf | 2,779 | text-generation |
| 76 | meta-llama/Llama-3.2-1B | 2,709 | text-generation |
| 77 | meta-llama/Llama-3.1-8B | 2,680 | text-generation |
| 78 | Qwen/Qwen-Image | 2,675 | text-to-image |
| 79 | stabilityai/sdxl-turbo | 2,654 | text-to-image |
| 80 | Qwen/Qwen-Image-Edit | 2,558 | image-to-image |
| 81 | Kijai/WanVideo_comfy | 2,553 | — |
| 82 | TokenRhythm/NeoHorse-1-4B | 2,551 | text-generation |
| 83 | hakurei/waifu-diffusion | 2,507 | text-to-image |
| 84 | microsoft/VibeVoice-1.5B | 2,502 | text-to-speech |
| 85 | deepseek-ai/DeepSeek-R1-0528 | 2,488 | text-generation |
| 86 | sesame/csm-1b | 2,481 | text-to-speech |
| 87 | xai-org/grok-1 | 2,476 | text-generation |
| 88 | meta-llama/Llama-2-7b-hf | 2,472 | text-generation |
| 89 | circlestone-labs/Anima | 2,460 | — |
| 90 | Qwen/Qwen2.5-7B-Instruct | 2,450 | text-generation |
| 91 | tiiuae/falcon-40b | 2,446 | text-generation |
| 92 | black-forest-labs/FLUX.2-dev | 2,437 | image-to-image |
| 93 | Lightricks/LTX-Video | 2,365 | image-to-video |
| 94 | Comfy-Org/MiniMax-H3 | 2,356 | — |
| 95 | tencent/HunyuanVideo | 2,340 | text-to-video |
| 96 | Qwen/Qwen3.6-27B | 2,332 | image-text-to-text |
| 97 | deepseek-ai/DeepSeek-V4-Flash | 2,327 | text-generation |
| 98 | microsoft/phi-4 | 2,326 | text-generation |
| 99 | pyannote/segmentation-3.0 | 2,322 | voice-activity-detection |
| 100 | ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF | 2,296 | image-text-to-text |