| 1 | Qwen2-Audio-7B-InstructQwen | Audio Text To Text | 97.4K | +97.4K | 561 | 8.4B |
| 2 | convnextv2_pico.fcmae_ft_in1ktimm | Image Classification | 97K | +97K | 1 | 9.1M |
| 3 | gemma-4-E2B-it-GGUFunsloth | Image Text to Text | 96.9K | +96.9K | 328 | — |
| 4 | byt5-smallgoogle | — | 96.4K | +96.4K | 106 | — |
| 5 | Qwen-Image-2512-GGUFunsloth | Text to Image | 96K | +96K | 426 | — |
| 6 | deepseek-r1-distill-qwen-32b-awqcasperhansen | — | 96K | +96K | 12 | 32.8B |
| 7 | Phi-4-mini-instructmicrosoft | Text Generation | 96K | +96K | 847 | 3.8B |
| 8 | rtdetr_v2_r18vdPekingU | Object Detection | 95.8K | +95.8K | 9 | 20.2M |
| 9 | bert-base-turkish-cased-mean-nli-stsb-tremrecan | Sentence Similarity | 95.6K | +95.6K | 53 | 111M |
| 10 | blip-vqa-baseSalesforce | Visual Question Answering | 95.5K | +95.5K | 196 | 385M |
| 11 | Qwen3-VL-Reranker-2BQwen | Text Ranking | 95.4K | +95.4K | 226 | 2.1B |
| 12 | Meta-Llama-3.1-8B-Instruct-GGUFbartowski | Text Generation | 95.4K | +95.4K | 411 | — |
| 13 | Qwen3.5-4B-BaseQwen | Image Text to Text | 95.4K | +95.4K | 106 | 4.7B |
| 14 | llama-nemotron-embed-1b-v2nvidia | Embeddings | 95.3K | +95.3K | 65 | 1.2B |
| 15 | Qwopus3.6-35B-A3B-Coder-MTP-GGUFJackrong | Image Text to Text | 95.2K | +95.2K | 248 | — |
| 16 | wide_resnet50_2.racm_in1ktimm | Image Classification | 94.8K | +94.8K | 2 | 69M |
| 17 | sd-turbostabilityai | Text to Image | 94.7K | +94.7K | 465 | 866M |
| 18 | whisper-large-v3-turbomlx-community | Speech Recognition | 94.7K | +94.7K | 115 | — |
| 19 | Florence-2-largemicrosoft | Image Text to Text | 94.6K | +94.6K | 1,870 | 777M |
| 20 | Meta-Llama-3-70B-Instructmeta-llama | Text Generation | 94.4K | +94.4K | 1,534 | 70.6B |
| 21 | Qwen-Image-Layered-GGUFunsloth | Image Text To Image | 94.4K | +94.4K | 68 | — |
| 22 | xlm-roberta-base-language-detectionpapluca | Text Classification | 94.4K | +94.4K | 377 | 278M |
| 23 | BiomedNLP-BiomedBERT-base-uncased-abstract-fulltextmicrosoft | Fill Mask | 94.3K | +94.3K | 337 | — |
| 24 | Llama-3.2-3B-Instruct-FP8RedHatAI | Text Generation | 94.2K | +94.2K | 6 | 3.6B |
| 25 | FLUX.1-schnellblack-forest-labs | Text to Image | 94.1K | +94.1K | 6,160 | 11.9B |
| 26 | Bio_Discharge_Summary_BERTemilyalsentzer | Fill Mask | 94K | +94K | 38 | — |
| 27 | distilbart-cnn-12-6sshleifer | Summarization | 94K | +94K | 326 | — |
| 28 | MERT-v1-95Mm-a-p | Audio Classification | 93.8K | +93.8K | 60 | — |
| 29 | Qwen3.5-27B-AWQQuantTrio | Image Text to Text | 93.6K | +93.6K | 42 | 27.8B |
| 30 | vlt5-base-keywordsVoicelab | Text Generation | 93.5K | +93.5K | 55 | 275M |
| 31 | DeepSeek-V3.1deepseek-ai | Text Generation | 93.3K | +93.3K | 833 | 685B |
| 32 | vit_base_patch16_224.augreg2_in21k_ft_in1ktimm | Image Classification | 93.2K | +93.2K | 14 | 86.6M |
| 33 | bge-small-en-v1.5Xenova | Embeddings | 93.2K | +93.2K | 20 | — |
| 34 | Bangla-twoclass-Sentiment-AnalyzerArunavaonly | Text Classification | 93.2K | +93.2K | 1 | 278M |
| 35 | Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUFDavidAU | Image Text to Text | 93.1K | +93.1K | 328 | — |
| 36 | boltzgen-1boltzgen | — | 92.8K | +92.8K | 6 | — |
| 37 | DeepSeek-V4-Flash-Basedeepseek-ai | — | 92.8K | +92.8K | 329 | 292B |
| 38 | Qwen3.5-2B-GGUFunsloth | Image Text to Text | 92.5K | +92.5K | 161 | — |
| 39 | snowflake-arctic-embed-xsSnowflake | Sentence Similarity | 92.4K | +92.4K | 43 | 22.6M |
| 40 | Qwopus3.6-27B-Coder-Compat-MTP-GGUFJackrong | Image Text to Text | 92.3K | +92.3K | 138 | — |
| 41 | Qwen3-Next-80B-A3B-InstructQwen | Text Generation | 92.3K | +92.3K | 1,057 | 81.3B |
| 42 | google_gemma-4-E2B-it-GGUFbartowski | Image Text to Text | 92.3K | +92.3K | 40 | — |
| 43 | wav2vec2-xlsr-53-espeak-cv-ftfacebook | Speech Recognition | 92.2K | +92.2K | 53 | — |
| 44 | nllb-200-distilled-1.3Bfacebook | Translation | 91.9K | +91.9K | 188 | — |
| 45 | mistral-7b-v0.3-bnb-4bitunsloth | Text Generation | 91.9K | +91.9K | 23 | 7.5B |
| 46 | Qwen3.5-4B-AWQ-4bitcyankiwi | Image Text to Text | 91.9K | +91.9K | 25 | 4.8B |
| 47 | vit_small_patch16_224.augreg_in21k_ft_in1ktimm | Image Classification | 91.9K | +91.9K | 4 | 22.1M |
| 48 | RealVisXL_V5.0SG161222 | Text to Image | 91.6K | +91.6K | 247 | 2.6B |
| 49 | autoformer-tourism-monthlyhuggingface | — | 91.6K | +91.6K | 11 | — |
| 50 | Qwen3-ForcedAligner-0.6BQwen | Speech Recognition | 91.5K | +91.5K | 164 | 918M |