| 1 | MiniMax-H3-pruned-NVFP4coolthor | Image Text To Video | 4 | ▲972.7%(up) | 36 | — |
| 2 | mms-tts-bgcfacebook | Text to Speech | 4 | — | 4 | 36.3M |
| 3 | Cosmos-Embed1-448p-anomaly-detectionnvidia | Video Classification | 4 | ▲4.6%(up) | 19 | 1.2B |
| 4 | opt-350mfacebook | Text Generation | 4 | ▲0.3%(up) | 155 | — |
| 5 | segformer-b4-finetuned-ade-512-512nvidia | Image Segmentation | 4 | ▲1.4%(up) | 8 | — |
| 6 | Nemotron-3-Labs-Ultra-Math-RLnvidia | Text Generation | 4 | — | 11 | 561B |
| 7 | Qwen2.5-72BQwen | Text Generation | 4 | ▲0.8%(up) | 108 | 72.7B |
| 8 | Qwen3-Nemotron-32B-GenRM-Principlenvidia | Text Generation | 4 | — | 22 | 32.8B |
| 9 | Qwen3.8-9B-Distill-GGUFempero-ai | Text Generation | 4 | ▲21.9%(up) | 307 | — |
| 10 | Qwen-Image-Edit-2511-Unblur-UpscaleprithivMLmods | Image To Image | 4 | ▲2.9%(up) | 196 | — |
| 11 | mms-tts-polfacebook | Text to Speech | 4 | — | 12 | 36.3M |
| 12 | Qwen3-4B-Instruct-2507-FP8Qwen | Text Generation | 4 | ▲2.2%(up) | 88 | 4.4B |
| 13 | sapiens-seg-0.3b-torchscriptfacebook | Image Segmentation | 4 | ▲3.9%(up) | 4 | — |
| 14 | Qwen2-1.5B-Instruct-GPTQ-Int8Qwen | Text Generation | 4 | — | 9 | 1.8B |
| 15 | Qwen3-30B-A3B-Thinking-2507-FP8Qwen | Text Generation | 4 | ▲1.0%(up) | 71 | 30.5B |
| 16 | tapex-large-finetuned-wtqmicrosoft | Table Question Answering | 4 | ▲0.1%(up) | 83 | 406M |
| 17 | AceInstruct-1.5Bnvidia | Text Generation | 4 | — | 26 | 1.8B |
| 18 | unispeech-sat-base-sdmicrosoft | — | 4 | — | 4 | — |
| 19 | ettin-encoder-1bjhu-clsp | Embeddings | 4 | ▲35.0%(up) | 33 | — |
| 20 | convnext-base-384-22k-1kfacebook | Image Classification | 4 | ▲0.2%(up) | 9 | — |
| 21 | Dayhoff-170M-UR90-HL-34000microsoft | Text Generation | 4 | — | 4 | 170M |
| 22 | swin-small-patch4-window7-224microsoft | Image Classification | 4 | ▲0.3%(up) | 6 | — |
| 23 | Magma-8Bmicrosoft | Robotics | 4 | ▲0.3%(up) | 422 | 8.9B |
| 24 | vit-large-patch16-224-in21kgoogle | Image Feature Extraction | 4 | ▲0.3%(up) | 35 | 304M |
| 25 | fibo-scene-analyzerbriaai | Image Text to Text | 4 | — | 48 | 36B |
| 26 | mms-tts-tirfacebook | Text to Speech | 4 | ▲0.9%(up) | 7 | 36.3M |
| 27 | Minitron-8B-Basenvidia | Text Generation | 4 | ▲0.4%(up) | 75 | — |
| 28 | llmlingua-2-bert-base-multilingual-cased-meetingbankmicrosoft | Token Classification | 4 | ▲1.9%(up) | 60 | 177M |
| 29 | Ling-3.0-tiny-abliterated-APEX-GGUFSC117 | Text Generation | 4 | ▲12.9%(up) | 39 | — |
| 30 | FluxSR-privatemon3tr | Image To Image | 4 | — | 4 | — |
| 31 | Xing4.0-29B-A4B-GGUFXingChen-AGI | Text Generation | 4 | — | 161 | — |
| 32 | MiniCPM5-1B-Agentic-Tooluse-v3-GGUFewin-reg | Text Generation | 4 | ▲53.6%(up) | 21 | — |
| 33 | Qwen2.5-Math-7B-PRM800KQwen | Text Classification | 4 | ▲0.4%(up) | 25 | 7.6B |
| 34 | Qwen3-TTS-Tokenizer-12HzQwen | Audio to Audio | 4 | ▲5.2%(up) | 98 | 171M |
| 35 | DaSiWa-WAN2.2-I2Vdarksidewalker | — | 4 | ▲1.3%(up) | 73 | — |
| 36 | AceMath-1.5B-Instructnvidia | Text Generation | 4 | — | 21 | 1.8B |
| 37 | Qwen3.8-Flash-Next-Sushi-3bpwbeamster | Image Text to Text | 4 | — | 9 | 28.8B |
| 38 | Qwen2-7B-Instruct-GPTQ-Int8Qwen | Text Generation | 4 | — | 21 | 7.6B |
| 39 | cocolm-largemicrosoft | — | 4 | — | 11 | — |
| 40 | Qwen1.5-0.5B-Chat-GPTQ-Int8Qwen | Text Generation | 4 | — | 9 | 464M |
| 41 | stable-video-diffusion-img2vid-xt-1-1-tensorrtstabilityai | Image To Video | 4 | — | 38 | — |
| 42 | long-t5-tglobal-largegoogle | — | 4 | — | 21 | 750M |
| 43 | Tev1-4B-experimentaltogethercomputer | Text Generation | 4 | — | 36 | 4.7B |
| 44 | embeddinggemma-2-8bitmlx-community | Embeddings | 4 | — | 7 | 744M |
| 45 | Realtime-VenusinclusionAI | Any to Any | 4 | — | 109 | — |
| 46 | Qwen3-1.7B-MLX-8bitQwen | Text Generation | 4 | — | 7 | 1.7B |
| 47 | C-RADIOv4-Hnvidia | Embeddings | 4 | ▲5.5%(up) | 89 | 652M |
| 48 | Cosmos-Reason2-8Bnvidia | Image Text to Text | 4 | ▲4.0%(up) | 241 | 8.8B |
| 49 | Llama-4-Scout-17B-16E-Instructmeta-llama | Image Text to Text | 4 | ▲0.5%(up) | 1,378 | 109B |
| 50 | t5-11b-ssm-nqgoogle | Text Generation | 4 | — | 4 | — |