| 1 | flux1-devComfy-Org | — | 297.4K | +297.4K | 682 | — |
| 2 | mivolo_v2iitolstykh | — | 297.3K | +297.3K | 33 | 28.8M |
| 3 | NVIDIA-Nemotron-3-Super-120B-A12B-BF16nvidia | Text Generation | 297.1K | +297.1K | 428 | 124B |
| 4 | wav2vec2-xls-r-300m-cs-250comodoro | Speech Recognition | 294.3K | +294.3K | 6 | 315M |
| 5 | MiniMax-M2.7MiniMaxAI | Text Generation | 293.9K | +293.9K | 1,248 | 229B |
| 6 | medgemma-4b-itgoogle | Image Text to Text | 293.4K | +293.4K | 1,081 | 4.3B |
| 7 | Qwen3.8-27B-nvfp4-NInferneroued | Image Text to Text | 293.4K | +293.4K | 100 | — |
| 8 | Qwen2.5-32B-Instruct-AWQQwen | Text Generation | 293.3K | +293.3K | 102 | 32.8B |
| 9 | GLM-5.3zai-org | Text Generation | 293.2K | +293.2K | 2,029 | 753B |
| 10 | Qwen3.6-27B-NVFP4unsloth | Image Text to Text | 292.9K | +292.9K | 281 | 21.2B |
| 11 | nomic-embed-text-v2-moenomic-ai | Sentence Similarity | 292.7K | +292.7K | 501 | 475M |
| 12 | qwen2_5vl-7b-lora-sft-CoT_traineval_4epochs_mergedcvis-tmu | — | 291.6K | +291.6K | 0 | 8.3B |
| 13 | LTX-2.3Lightricks | Image To Video | 290.8K | +290.8K | 1,923 | — |
| 14 | docling-modelsdocling-project | — | 289.2K | +289.2K | 219 | — |
| 15 | Qwen3-TTS-12Hz-0.6B-CustomVoiceQwen | Text to Speech | 287.1K | +287.1K | 193 | 906M |
| 16 | Meta-Llama-3-8B-Instructmeta-llama | Text Generation | 285.7K | +285.7K | 5,165 | 8B |
| 17 | table-transformer-structure-recognitionmicrosoft | Object Detection | 285.7K | +285.7K | 231 | 28.8M |
| 18 | rtdetr_r101vd_coco_o365PekingU | Object Detection | 285K | +285K | 19 | 76.8M |
| 19 | tiny-random-OPTForCausalLMpeft-internal-testing | Text Generation | 284.6K | +284.6K | 0 | 812.4K |
| 20 | Ornith-1.5-397B-GGUFornith-ai | Text Generation | 284.2K | +284.2K | 40 | — |
| 21 | DNABERT-2-117Mzhihan1996 | — | 284.1K | +284.1K | 113 | — |
| 22 | gemma-4-E4B-it-MLX-4bitlmstudio-community | Any to Any | 281.6K | +281.6K | 26 | 8B |
| 23 | splade-cocondenser-selfdistilnaver | Embeddings | 280.7K | +280.7K | 11 | — |
| 24 | wav2vec2-xls-r-300m-hebrewimvladikon | Speech Recognition | 280.6K | +280.6K | 7 | 315M |
| 25 | albert-base-v2albert | Fill Mask | 280.5K | +280.5K | 151 | 11.8M |
| 26 | gte-large-en-v1.5Alibaba-NLP | Sentence Similarity | 279K | +279K | 239 | 434M |
| 27 | dragon-multiturn-query-encodernvidia | Embeddings | 278.1K | +278.1K | 61 | — |
| 28 | dragon-multiturn-context-encodernvidia | Embeddings | 278.1K | +278.1K | 25 | — |
| 29 | timesfm-3.0-pytorchgoogle | Time Series Forecasting | 277.7K | +277.7K | 911 | 331M |
| 30 | nb-wav2vec2-1b-nynorskNbAiLab | Speech Recognition | 275.5K | +275.5K | 1 | 963M |
| 31 | gemma-4-E4B-it-MLX-8bitlmstudio-community | Any to Any | 274.7K | +274.7K | 12 | 8B |
| 32 | efficientnet_b0.ra_in1ktimm | Image Classification | 274K | +274K | 10 | 5.3M |
| 33 | gemma-4-E4B-it-MLX-6bitlmstudio-community | Any to Any | 273.9K | +273.9K | 4 | 8B |
| 34 | gemma-4-E4B-it-MLX-5bitlmstudio-community | Any to Any | 273.7K | +273.7K | 0 | 8B |
| 35 | tiny-Qwen3ForCausalLMtrl-internal-testing | Text Generation | 271.3K | +271.3K | 2 | 2.5M |
| 36 | Qwen3.6-35B-A3B-AWQQuantTrio | Image Text to Text | 268.7K | +268.7K | 37 | 36B |
| 37 | wav2vec2-large-xlsr-koreankresnik | Speech Recognition | 268.6K | +268.6K | 56 | 317M |
| 38 | siglip2-base-patch16-naflexgoogle | Zero-Shot Image Classification | 265.6K | +265.6K | 40 | 375M |
| 39 | chronos-bolt-tinyamazon | Time Series Forecasting | 265.6K | +265.6K | 30 | 8.7M |
| 40 | EXAONE-3.5-7.8B-Instruct-AWQLGAI-EXAONE | Text Generation | 265.3K | +265.3K | 18 | 7.8B |
| 41 | DeepSeek-Coder-V2-Lite-Instructdeepseek-ai | Text Generation | 265K | +265K | 668 | 15.7B |
| 42 | LFM2.5-2.6B-GGUFLiquidAI | Text Generation | 264.5K | +264.5K | 360 | — |
| 43 | HyperCLOVAX-SEED-Text-Instruct-1.5B-Q4_K_M-GGUFrippertnt | — | 262.6K | +262.6K | 5 | — |
| 44 | manga-ocr-basekha-white | Image to Text | 261.2K | +261.2K | 183 | — |
| 45 | Qwen3.6-35B-A3B-MTP-GGUFunsloth | Image Text to Text | 261K | +261K | 964 | — |
| 46 | Kronos-smallNeoQuasar | Time Series Forecasting | 260.8K | +260.8K | 34 | 24.7M |
| 47 | gte-smallthenlper | Sentence Similarity | 260.5K | +260.5K | 191 | 33.4M |
| 48 | Qwen3-ASR-1.7BQwen | Speech Recognition | 260K | +260K | 1,137 | 2.3B |
| 49 | flan-t5-basegoogle | — | 258.7K | +258.7K | 1,094 | 248M |
| 50 | Qwen3.5-9B-AWQQuantTrio | Image Text to Text | 257.6K | +257.6K | 28 | 9.7B |