| 1 | gemma-3-12b-it-norm-preserved-biprojected-abliteratedgrimjim | Image Text to Text | 2 | — | 31 | 12.2B |
| 2 | DiarizationLM-13b-Fisher-v1google | Text Generation | 2 | — | 18 | 13B |
| 3 | gemma-4-E4B-it-qat-mobile-ctgoogle | Any to Any | 2 | ▲2.0%(up) | 34 | 8.7B |
| 4 | gemma-4-E2B-it-qat-q4_0-unquantized-assistantgoogle | Any to Any | 2 | — | 27 | 78M |
| 5 | Llama-3.1-Nemotron-Nano-VL-8B-V1nvidia | Image Text to Text | 2 | ▲0.1%(up) | 188 | 8.7B |
| 6 | beit-large-patch16-512microsoft | Image Classification | 2 | ▲0.1%(up) | 20 | — |
| 7 | Phoenix-X-26B-A4B-Heretic-GGUFmradermacher | — | 2 | 0% | 2 | — |
| 8 | MIMESIS-4Bphanviethoang1512 | Text Generation | 2 | — | 3 | 5.2B |
| 9 | NigerianAccentedEnglishNCAIR1 | Speech Recognition | 2 | ▲0.8%(up) | 40 | — |
| 10 | CodeQwen1.5-7B-AWQQwen | Text Generation | 2 | ▲0.1%(up) | 9 | 7.3B |
| 11 | SmolVLM-256M-InstructHuggingFaceTB | Image Text to Text | 2 | ▲1.4%(up) | 423 | 256M |
| 12 | efficientnet-b3google | Image Classification | 2 | ▲1.1%(up) | 16 | — |
| 13 | vit-large-patch32-384google | Image Classification | 2 | ▲0.1%(up) | 22 | — |
| 14 | bekko-embedding-v1-a8mhotchpotch | Sentence Similarity | 2 | ▲17.6%(up) | 24 | 106M |
| 15 | Thomson-1.0-Small-APEX-I-MiniPlus-V2.1-GGUFIsValorum | Text Generation | 2 | — | 3 | — |
| 16 | Ternary-Bonsai-2-27B-Abliterated-v2-PQ2_0-MTP-GGUF-3060-benchgroxaxo | Text Generation | 2 | — | 3 | — |
| 17 | LFM2.5-24B-A2B-APEX-I-NanoPlus-GGUFIsValorum | Text Generation | 2 | — | 3 | — |
| 18 | Dayhoff-170M-GR-31000microsoft | Text Generation | 2 | — | 4 | 170M |
| 19 | tapex-large-finetuned-tabfactmicrosoft | Table Question Answering | 2 | ▲0.1%(up) | 15 | — |
| 20 | layoutlmv3-base-chinesemicrosoft | — | 2 | ▲0.6%(up) | 89 | — |
| 21 | Qwen3-235B-A22B-FP8Qwen | Text Generation | 2 | ▲0.3%(up) | 103 | 235B |
| 22 | MiniMax-H3-Looping-Sketch-AnimeInner-Reflections | — | 2 | — | 83 | — |
| 23 | conditional-detr-resnet-50microsoft | Object Detection | 2 | ▲1.8%(up) | 22 | 43.5M |
| 24 | llm-jp-4.1-8b-thinkingllm-jp | Text Generation | 2 | — | 16 | 8.6B |
| 25 | codebert-basemicrosoft | Embeddings | 2 | ▲0.1%(up) | 299 | — |
| 26 | laya-multilingual-GGUFmys | — | 2 | — | 15 | — |
| 27 | Qwen3-VL-8B-ComfyUInynxz | Image Text to Text | 2 | — | 4 | — |
| 28 | Mizan-27B-Turkish-Legal-LLM-Q4_K_M-GGUFAlicanKiraz0 | Image Text to Text | 2 | ▲1.2%(up) | 45 | — |
| 29 | gemma-4-12b-it-uncensored-GGUFzaakirio | Image Text to Text | 2 | ▲6.8%(up) | 72 | — |
| 30 | Qwen2.5-14B-Instruct-GPTQ-Int4Qwen | Text Generation | 2 | ▲3.0%(up) | 33 | 14.8B |
| 31 | VibeVoice-AcousticTokenizermicrosoft | Embeddings | 2 | ▲1.4%(up) | 20 | 687M |
| 32 | MiniMax-H3-FP8unsloth | Image Text To Video | 2 | — | 17 | — |
| 33 | Dayhoff-170M-UR90-HL-44000microsoft | Text Generation | 2 | — | 4 | 170M |
| 34 | Qwen3-1.7B-MLX-bf16Qwen | Text Generation | 2 | 0% | 12 | 1.7B |
| 35 | xlm-clm-ende-1024FacebookAI | Fill Mask | 2 | ▲0.0%(up) | 4 | 209M |
| 36 | git-base-vqav2microsoft | Visual Question Answering | 2 | — | 25 | 177M |
| 37 | MiniMax-H3-Prompt-Rewriter-LoRA-8Blightx2v | Image Text to Text | 2 | — | 48 | — |
| 38 | Llama-3.1-70B-Instructmeta-llama | Text Generation | 2 | ▲0.1%(up) | 1,012 | 70.6B |
| 39 | pegasus-largegoogle | Summarization | 2 | ▲0.1%(up) | 113 | — |
| 40 | Bonsai-2-27B-Ternary-CRACK-GGUFdealignai | Text Generation | 2 | — | 167 | — |
| 41 | t5-3b-ssm-nqgoogle | Text Generation | 2 | — | 5 | — |
| 42 | Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUFIsValorum | Text Generation | 2 | — | 8 | — |
| 43 | kova-tts-1kova-ai | Text to Speech | 2 | — | 9 | 1.3B |
| 44 | JenniferConnellyEarly90s_krea2xixxix-HF | Text to Image | 2 | ▲4.5%(up) | 13 | — |
| 45 | Ming-omni-tts-0.5BinclusionAI | Text to Speech | 2 | ▲9.3%(up) | 43 | 1.6B |
| 46 | AnyJev-Tacitus-31B-GGUFmradermacher | — | 2 | — | 2 | — |
| 47 | git-large-cocomicrosoft | Image to Text | 2 | ▲0.2%(up) | 111 | 394M |
| 48 | so101-reachnvidia | Reinforcement Learning | 2 | — | 2 | — |
| 49 | DeepSeek-V4-Flash-IQ2XXS-TM64-Q4KAttention-v1erayyapagci | Text Generation | 2 | — | 2 | — |
| 50 | MiniCPM-Llama3-V-2_5openbmb | Image Text to Text | 2 | ▲0.5%(up) | 1,421 | 8.5B |