| 1 | Naive-N0.5-Flash-JANGHT2.5JANGQ-AI | Text Generation | 2 | — | 2 | 29B |
| 2 | antalia-1cloud0day3 | Text to Speech | 2 | — | 11 | 305M |
| 3 | mbart-large-50facebook | — | 2 | ▲0.1%(up) | 169 | — |
| 4 | deberta-base-mnlimicrosoft | Text Classification | 2 | ▲0.3%(up) | 11 | — |
| 5 | Swift-Bonsai-2-27B-Katana-MTP-GGUFayshinko | Image Text to Text | 2 | — | 6 | — |
| 6 | deberta-xxlarge-v2-mnlimicrosoft | — | 2 | — | 2 | — |
| 7 | tipsv2-g14google | Zero-Shot Image Classification | 2 | ▲3.5%(up) | 32 | 1.5B |
| 8 | ISOM-Falcon-40BPrannesshkva | Text Generation | 2 | 0% | 2 | 41.8B |
| 9 | Phi-3-medium-128k-instruct-onnx-cudamicrosoft | Text Generation | 2 | — | 26 | — |
| 10 | swinv2-tiny-patch4-window8-256microsoft | Image Classification | 2 | ▲0.8%(up) | 14 | — |
| 11 | JEMMMaestroYan | — | 2 | — | 28 | — |
| 12 | ThinkingCap-Qwen3.8-27B-NInferSchestex | Text Generation | 2 | — | 5 | — |
| 13 | Qwopus3.8-27B-FlashJackrong | Image Text to Text | 2 | ▲28.5%(up) | 57 | 27.8B |
| 14 | GEM-Xnvidia | — | 2 | ▲3.3%(up) | 29 | — |
| 15 | MiMo-V2.6-Flash-RL-MLX-4bit-MTPVontra | Text Generation | 2 | — | 11 | 309B |
| 16 | t5-efficient-tiny-nl6google | — | 2 | — | 2 | — |
| 17 | SAE-Res-Qwen3.5-35B-A3B-Base-W32K-L0_50Qwen | — | 2 | — | 12 | — |
| 18 | OrcaSAQ-2-27Borcarouter | Text Generation | 2 | — | 281 | 6.8B |
| 19 | Wan2.1-VACE-14BWan-AI | Image To Video | 2 | ▲3.6%(up) | 518 | 17.3B |
| 20 | siglip2-so400m-patch16-256google | Zero-Shot Image Classification | 2 | ▲3.2%(up) | 9 | 1.1B |
| 21 | larger_clap_musiclaion | Embeddings | 2 | ▲1.5%(up) | 53 | — |
| 22 | LongCat-Video-Avatar-1.5-GGUF-ComfyUIvantagewithai | — | 2 | ▲25.9%(up) | 25 | — |
| 23 | WorldReward-qwen35-9b-GGUFprithivMLmods | Image Text to Text | 2 | — | 2 | — |
| 24 | mask2former-swin-small-cityscapes-semanticfacebook | Image Segmentation | 2 | ▲0.4%(up) | 5 | 68.8M |
| 25 | webssl-dino3b-light2b-224facebook | Image Feature Extraction | 2 | — | 2 | 2.9B |
| 26 | baguettotron-600mPleIAs | Text Generation | 2 | — | 31 | 608M |
| 27 | DAM-3Bnvidia | Image Text to Text | 2 | ▲1.1%(up) | 132 | — |
| 28 | MiniCPM5-Pashto-Native-GGUFnassimjp | Text Generation | 2 | — | 2 | — |
| 29 | MAI-UI-8BTongyi-MAI | Image Text to Text | 2 | ▲0.4%(up) | 204 | 8.8B |
| 30 | Qwen3.8-27B-pi-RCO-allocation-transfer-GGUFfiretussin | — | 2 | — | 2 | — |
| 31 | Qwen3.8-27B-MTPLX-Optimized-QualityYoussofal | Text Generation | 2 | ▲9.5%(up) | 69 | 27.4B |
| 32 | tapas-large-finetuned-sqagoogle | Table Question Answering | 2 | ▲3.3%(up) | 9 | — |
| 33 | Phi-3-medium-4k-instruct-onnx-cpumicrosoft | Text Generation | 2 | — | 9 | — |
| 34 | Qwen3-0.6B-MLX-8bitQwen | Text Generation | 2 | — | 7 | 596M |
| 35 | Qwen3-8B-MatGPTQISTA-DASLab | Text Generation | 2 | — | 3 | 8.3B |
| 36 | metricx-24-hybrid-large-v2p6-bfloat16google | — | 2 | ▲2.6%(up) | 6 | — |
| 37 | Qwen-Image-2.1-Fun-Acc-LoRAsalibaba-pai | Text to Image | 2 | — | 46 | — |
| 38 | roberta-hate-speech-dynabench-r4-targetfacebook | Text Classification | 2 | ▲0.1%(up) | 103 | 125M |
| 39 | tipsv2-l14-dptgoogle | Depth Estimation | 2 | ▲1.4%(up) | 9 | 406M |
| 40 | dino-vits16facebook | Image Feature Extraction | 2 | ▲0.5%(up) | 18 | — |
| 41 | Kandinsky-6.0-VSR-5s-Diffuserskandinskylab | Any to Any | 2 | — | 15 | 1.4B |
| 42 | imagine-v9Interchained | Text Generation | 2 | — | 2 | 1.3B |
| 43 | Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-abliterated-OptiQ-3.7bpw-mlxlemuralabs | Text Generation | 2 | ▲1.3%(up) | 19 | 26.9B |
| 44 | segformer-b3-finetuned-ade-512-512nvidia | Image Segmentation | 2 | ▲5.0%(up) | 16 | — |
| 45 | DeepSeek-V4.1-Flash-ROCMFP23-GGUFLucebox | — | 2 | — | 10 | — |
| 46 | hubert-large-ls960-ftfacebook | Speech Recognition | 2 | ▲0.9%(up) | 80 | — |
| 47 | RealtimeWAMlightx2v | — | 2 | — | 14 | — |
| 48 | IndustryLLMalibaba-multimodal-industrial-ai | Text Generation | 2 | — | 3 | 35.1B |
| 49 | EUPE-ViT-Sfacebook | — | 2 | ▲1.6%(up) | 12 | — |
| 50 | Qwen3.8-Flash-Next-W8A8-DYNAMIC-300imatteiuspi | Image Text to Text | 2 | — | 5 | — |