| 1 | Qwen3-VL-235B-A22B-InstructQwen | Image Text to Text | 86.1K | +86.1K | 421 | 236B |
| 2 | Qwen3.8-27B-Ridge-GGUFempero-ai | Image Text to Text | 86.1K | +86.1K | 361 | — |
| 3 | nli-deberta-v3-smallcross-encoder | Zero-Shot Classification | 85.8K | +85.8K | 16 | 142M |
| 4 | multilingual-e5-large-onnxQdrant | Sentence Similarity | 85.8K | +85.8K | 4 | — |
| 5 | Dark-Scarlett-v0.3-26B-A4B-GGUFReadyArt | — | 85.8K | +85.8K | 15 | — |
| 6 | Llama-3.3-70B-Instructmeta-llama | Text Generation | 85.8K | +85.8K | 3,110 | 70.6B |
| 7 | Qwen-AgentWorld-35B-A3B-GGUFunsloth | Text Generation | 85.7K | +85.7K | 249 | — |
| 8 | DA3METRIC-LARGEdepth-anything | Depth Estimation | 85.6K | +85.6K | 28 | 334M |
| 9 | Ornith-1.5-9B-OBLITERATEDOBLITERATUS | Text Generation | 85.6K | +85.6K | 79 | 9.7B |
| 10 | small-Qwen3ForCausalLMtrl-internal-testing | Text Generation | 85.6K | +85.6K | 0 | 19.9M |
| 11 | thomsonreuters_Thomson-1.0-Small-GGUFbartowski | Image Text to Text | 85.5K | +85.5K | 19 | — |
| 12 | NVIDIA-Nemotron-3-Nano-4B-BF16nvidia | Text Generation | 85.5K | +85.5K | 129 | 4B |
| 13 | potion-base-8Mminishlab | — | 85.4K | +85.4K | 82 | 7.6M |
| 14 | Devstral-Small-2-24B-Instruct-2512mistralai | — | 85.4K | +85.4K | 673 | 24B |
| 15 | Qwen3.6-27B-NVFP4-MTP-GGUFmichaelw9999 | — | 85.4K | +85.4K | 63 | — |
| 16 | gte-base-en-v1.5Alibaba-NLP | Sentence Similarity | 85.3K | +85.3K | 72 | 137M |
| 17 | whisper-large-v3-turbo-ggufhandy-computer | Speech Recognition | 85.2K | +85.2K | 4 | — |
| 18 | FLUX.1-Kontext-devblack-forest-labs | Image To Image | 85.2K | +85.2K | 2,870 | 11.9B |
| 19 | privacy-filter-multilingual-GGUFLocalAI-io | Token Classification | 85.1K | +85.1K | 6 | — |
| 20 | Mistral-Small-3.1-24B-Instruct-2503mistralai | — | 85K | +85K | 1,384 | 24B |
| 21 | openai-gptopenai-community | Text Generation | 85K | +85K | 317 | 120M |
| 22 | Serenity-26B-A4B-GGUFReadyArt | — | 84.7K | +84.7K | 21 | — |
| 23 | Z-Image-LoranphSi | Text to Image | 84.7K | +84.7K | 161 | — |
| 24 | mmBERT-basejhu-clsp | Fill Mask | 84.7K | +84.7K | 260 | — |
| 25 | Step-3.7-Flash-NVFP4stepfun-ai | Image Text to Text | 84.6K | +84.6K | 64 | 104B |
| 26 | GLM-5.2-GGUFunsloth | Text Generation | 84.6K | +84.6K | 648 | — |
| 27 | Muse-Glimmer-30Bmeta-models | Image Text to Text | 84.5K | +84.5K | 1,990 | 29.8B |
| 28 | Kimi-K2.7-Code-GGUFunsloth | Image Text to Text | 84.3K | +84.3K | 196 | — |
| 29 | vit_base_patch8_224.augreg2_in21k_ft_in1ktimm | Image Classification | 84.2K | +84.2K | 4 | 86.6M |
| 30 | Agents-A1-4BInternScience | Text Generation | 84.1K | +84.1K | 101 | 4.5B |
| 31 | Qwen3-4B-AWQQwen | Text Generation | 83.9K | +83.9K | 33 | 4B |
| 32 | vit-age-classifiernateraw | Image Classification | 83.9K | +83.9K | 149 | 85.8M |
| 33 | HunyuanDiT-v1.1-Diffusers-DistilledTencent-Hunyuan | Text to Image | 83.7K | +83.7K | 19 | 1.5B |
| 34 | Kimi-K2.6moonshotai | Image Text to Text | 83.5K | +83.5K | 1,613 | 1T |
| 35 | rubert-base-cased-sentiment-rusentimentblanchefort | Text Classification | 83.3K | +83.3K | 15 | 178M |
| 36 | Qwen3.6-14B-A3B-FableVibes-GGUFtvall43 | Text Generation | 83.3K | +83.3K | 198 | — |
| 37 | Cosmos-Reason2-8Bnvidia | Image Text to Text | 83.3K | +83.3K | 235 | 8.8B |
| 38 | bert-base-japanese-whole-word-maskingtohoku-nlp | Fill Mask | 83.2K | +83.2K | 76 | — |
| 39 | nli-mpnet-base-v2sentence-transformers | Sentence Similarity | 83K | +83K | 15 | 109M |
| 40 | phi-4microsoft | Text Generation | 83K | +83K | 2,316 | 14.7B |
| 41 | gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-GGUFllmfan46 | Image Text to Text | 83K | +83K | 78 | — |
| 42 | Llama-3.2-1B-Instruct-FP8-dynamicRedHatAI | Text Generation | 82.9K | +82.9K | 4 | 1.5B |
| 43 | privacy-filteropenai | Token Classification | 82.9K | +82.9K | 1,783 | 1.4B |
| 44 | Qwen3-VL-30B-A3B-InstructQwen | Image Text to Text | 82.8K | +82.8K | 610 | 31.1B |
| 45 | FLUX.2-klein-4Bblack-forest-labs | Image To Image | 82.8K | +82.8K | 1,011 | 3.9B |
| 46 | audio.cpptrklou | — | 82.6K | +82.6K | 0 | — |
| 47 | Clinical-Longformeryikuan8 | Fill Mask | 82.4K | +82.4K | 69 | — |
| 48 | Tiel-Coder-35B-A3B-GGUFpeculiar-ragdoll | Image Text to Text | 82.3K | +82.3K | 371 | — |
| 49 | wav2vec2-large-xls-r-300m-sinhala-low-LR-part1SpideyDLK | Speech Recognition | 82.2K | +82.2K | 0 | 316M |
| 50 | BiomedNLP-BiomedBERT-base-uncased-abstractmicrosoft | Fill Mask | 82.1K | +82.1K | 101 | — |