Snapshot 2026-10-21. Likes measure Hub popularity, not quality. Datasets · Methodology.
| Rank | Model | Likes | Task |
|---|---|---|---|
| 201 | Salesforce/blip-image-captioning-large | 1,500 | image-to-text |
| 202 | Qwen/Qwen-Image-Edit-2511 | 1,489 | image-to-image |
| 203 | google-bert/bert-base-chinese | 1,485 | fill-mask |
| 204 | city96/FLUX.1-dev-gguf | 1,483 | text-to-image |
| 205 | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 | 1,482 | sentence-similarity |
| 206 | microsoft/Phi-3-mini-4k-instruct | 1,476 | text-generation |
| 207 | monster-labs/control_v1p_sd15_qrcode_monster | 1,475 | — |
| 208 | comfyanonymous/flux_text_encoders | 1,473 | — |
| 209 | MiniMaxAI/MiniMax-Music3 | 1,466 | text-to-audio |
| 210 | apple/OpenELM | 1,457 | — |
| 211 | fishaudio/s2-pro | 1,454 | text-to-speech |
| 212 | webui/ControlNet-modules-safetensors | 1,453 | — |
| 213 | facebook/dinov3-vitl16-pretrain-lvd1689m | 1,450 | image-feature-extraction |
| 214 | h94/IP-Adapter | 1,444 | text-to-image |
| 215 | vikhyatk/moondream2 | 1,443 | image-text-to-text |
| 216 | stabilityai/sd-vae-ft-mse-original | 1,433 | text-to-image |
| 217 | XHToken/Spark-X2.5-4B | 1,428 | text-generation |
| 218 | prism-ml/Ternary-Bonsai-27B-gguf | 1,427 | text-generation |
| 219 | moonshotai/Kimi-K2.7-Code | 1,422 | image-text-to-text |
| 220 | stabilityai/stable-diffusion-xl-base-0.9 | 1,420 | text-to-image |
| 221 | openbmb/MiniCPM-Llama3-V-2_5 | 1,419 | image-text-to-text |
| 222 | zai-org/GLM-4.5 | 1,417 | text-generation |
| 223 | mistralai/Mistral-Small-3.1-24B-Instruct-2503 | 1,404 | — |
| 224 | black-forest-labs/FLUX.2-klein-base-9b-fp8 | 1,393 | image-to-image |
| 225 | sentence-transformers/all-mpnet-base-v2 | 1,392 | sentence-similarity |
| 226 | Qwen/Qwen3-Coder-480B-A35B-Instruct | 1,382 | text-generation |
| 227 | microsoft/TRELLIS.2-4B | 1,380 | image-to-3d |
| 228 | meta-llama/Llama-4-Scout-17B-16E-Instruct | 1,378 | image-text-to-text |
| 229 | genmo/mochi-1-preview | 1,374 | text-to-video |
| 230 | microsoft/OmniParser-v2.0 | 1,373 | — |
| 231 | MiniMaxAI/MiniMax-M2.1 | 1,370 | text-generation |
| 232 | microsoft/phi-1_5 | 1,368 | text-generation |
| 233 | ByteDance/Hyper-SD | 1,361 | text-to-image |
| 234 | mistralai/Codestral-22B-v0.1 | 1,361 | — |
| 235 | pyannote/speaker-diarization | 1,355 | automatic-speech-recognition |
| 236 | kyutai/pocket-tts | 1,351 | — |
| 237 | stabilityai/stable-cascade | 1,344 | text-to-image |
| 238 | dots-studio/dots.ocr | 1,341 | image-text-to-text |
| 239 | unsloth/Qwen3.6-27B-MTP-GGUF | 1,337 | image-text-to-text |
| 240 | stable-diffusion-v1-5/stable-diffusion-v1-5 | 1,330 | text-to-image |
| 241 | zai-org/glm-4-9b-chat | 1,329 | — |
| 242 | Qwen/Qwen3.8-2.4T-A95B | 1,323 | text-generation |
| 243 | openbmb/MiniCPM-o-2_6 | 1,321 | any-to-any |
| 244 | microsoft/VibeVoice-ASR | 1,316 | automatic-speech-recognition |
| 245 | 01-ai/Yi-34B | 1,312 | text-generation |
| 246 | google/diffusiongemma-26B-A4B-it | 1,310 | image-text-to-text |
| 247 | XingChen-AGI/TeleOCR | 1,307 | image-text-to-text |
| 248 | microsoft/VibeVoice-Realtime-0.5B | 1,305 | text-to-speech |
| 249 | stabilityai/stable-fast-3d | 1,305 | image-to-3d |
| 250 | Qwen/Qwen3-Embedding-0.6B | 1,304 | feature-extraction |
| 251 | Qwen/Qwen3-Coder-30B-A3B-Instruct | 1,298 | text-generation |
| 252 | tencent/Hunyuan3D-2.1 | 1,297 | image-to-3d |
| 253 | Wan-AI/Wan2.2-Animate-14B | 1,295 | video-to-video |
| 254 | Qwen/Qwen2-VL-7B-Instruct | 1,293 | image-text-to-text |
| 255 | google/flan-t5-xxl | 1,290 | — |
| 256 | ibm-granite/granite-docling-258M | 1,281 | image-text-to-text |
| 257 | microsoft/Phi-3.5-mini-instruct | 1,281 | text-generation |
| 258 | ProsusAI/finbert | 1,281 | text-classification |
| 259 | Tongyi-MAI/Z-Image | 1,279 | text-to-image |
| 260 | intfloat/multilingual-e5-large | 1,277 | feature-extraction |
| 261 | BAAI/bge-reranker-v2-m3 | 1,271 | text-classification |
| 262 | XLabs-AI/flux-RealismLora | 1,271 | text-to-image |
| 263 | black-forest-labs/FLUX.1-Fill-dev | 1,269 | — |
| 264 | dphn/dolphin-2.5-mixtral-8x7b | 1,268 | text-generation |
| 265 | openai/clip-vit-base-patch32 | 1,266 | zero-shot-image-classification |
| 266 | google/gemma-2b | 1,263 | text-generation |
| 267 | google/gemma-7b-it | 1,262 | text-generation |
| 268 | tencent/Hy-MT2-1.8B | 1,261 | translation |
| 269 | MiniMaxAI/MiniMax-M2.7 | 1,257 | text-generation |
| 270 | Qwen/Qwen-Image-Edit-2509 | 1,257 | image-to-image |
| 271 | prompthero/openjourney-v4 | 1,255 | text-to-image |
| 272 | google/gemma-3-1b-it | 1,252 | text-generation |
| 273 | unsloth/Qwen3.8-Flash-Next-GGUF | 1,245 | image-text-to-text |
| 274 | openbmb/MiniCPM-V-4.6 | 1,241 | image-text-to-text |
| 275 | zai-org/GLM-4.6 | 1,241 | text-generation |
| 276 | stabilityai/stable-diffusion-3.5-medium | 1,238 | text-to-image |
| 277 | ByteDance-Seed/BAGEL-7B-MoT | 1,234 | any-to-any |
| 278 | unsloth/gemma-4-26B-A4B-it-GGUF | 1,234 | image-text-to-text |
| 279 | lj1995/VoiceConversionWebUI | 1,231 | — |
| 280 | nvidia/nemotron-3.5-asr-streaming-0.6b | 1,223 | automatic-speech-recognition |
| 281 | SWivid/F5-TTS | 1,219 | text-to-speech |
| 282 | nvidia/parakeet-tdt-0.6b-v3 | 1,217 | automatic-speech-recognition |
| 283 | stabilityai/stable-video-diffusion-img2vid-xt-1-1 | 1,217 | image-to-video |
| 284 | Qwen/Qwen3-VL-8B-Instruct | 1,215 | image-text-to-text |
| 285 | baidu/Qianfan-OCR | 1,212 | image-text-to-text |
| 286 | Falconsai/nsfw_image_detection | 1,211 | image-classification |
| 287 | impira/layoutlm-document-qa | 1,208 | document-question-answering |
| 288 | ai21labs/Jamba-v0.1 | 1,201 | text-generation |
| 289 | CohereLabs/cohere-transcribe-03-2026 | 1,200 | automatic-speech-recognition |
| 290 | Qwen/Qwen3-ASR-1.7B | 1,199 | automatic-speech-recognition |
| 291 | tencent/HY-MT1.5-1.8B | 1,190 | translation |
| 292 | xai-org/grok-2 | 1,190 | — |
| 293 | m-a-p/YuE2-3B | 1,185 | text-to-audio |
| 294 | Nanbeige/Nanbeige4.1-3B | 1,185 | text-generation |
| 295 | timbrooks/instruct-pix2pix | 1,185 | image-to-image |
| 296 | tiiuae/falcon-40b-instruct | 1,183 | text-generation |
| 297 | Qwen/Qwen-Image-Layered | 1,178 | image-text-to-image |
| 298 | zai-org/chatglm3-6b | 1,173 | — |
| 299 | black-forest-labs/flux-3-image-klein-comfy | 1,172 | image-to-image |
| 300 | openbmb/MiniCPM5-1B | 1,172 | text-generation |