| 1 | esmfold_v1facebook | — | 3 | ▲0.3%(up) | 60 | — |
| 2 | galactica-125mfacebook | Text Generation | 3 | ▲0.0%(up) | 43 | 125M |
| 3 | pix2struct-docvqa-largegoogle | Visual Question Answering | 3 | — | 39 | — |
| 4 | Phi-4-mini-instruct-GGUFunsloth | Text Generation | 3 | ▲4.7%(up) | 158 | — |
| 5 | sam2-hiera-smallfacebook | Mask Generation | 3 | ▲0.4%(up) | 20 | 46M |
| 6 | Qwen2.5-Coder-32B-Instruct-abliterated-GGUFbartowski | Text Generation | 3 | ▲2.9%(up) | 61 | — |
| 7 | t5-efficient-base-dl8google | — | 3 | — | 5 | — |
| 8 | t5-efficient-small-nl22google | — | 3 | — | 3 | — |
| 9 | vit-hybrid-base-bit-384google | Image Classification | 3 | — | 9 | 99M |
| 10 | Qwen-1_8B-Chat-Int4Qwen | Text Generation | 3 | — | 40 | 1.8B |
| 11 | stt_fa_fastconformer_hybrid_largenvidia | Speech Recognition | 3 | ▲0.2%(up) | 30 | — |
| 12 | t5-efficient-large-nl16google | — | 3 | — | 4 | — |
| 13 | MiniMax-H3-GGUFleejet | Image To Video | 3 | ▲32.0%(up) | 26 | — |
| 14 | Qwen1.5-0.5B-Chat-GPTQ-Int4Qwen | Text Generation | 3 | ▲0.9%(up) | 16 | 464M |
| 15 | table-transformer-structure-recognition-v1.1-finmicrosoft | Object Detection | 3 | ▲2.1%(up) | 5 | 28.8M |
| 16 | detr-resnet-50-dc5facebook | Object Detection | 3 | ▲0.2%(up) | 10 | 41.6M |
| 17 | mms-tts-kaafacebook | Text to Speech | 3 | ▲91.6%(up) | 6 | 36.3M |
| 18 | mask2former-swin-large-cityscapes-panopticfacebook | Image Segmentation | 3 | ▲0.8%(up) | 6 | 216M |
| 19 | CYBER-FROST-3.8-GGUFfreakyskittle | Image Text to Text | 3 | — | 22 | — |
| 20 | Muse-Glimmer-30B-assistantmeta-models | Image Text to Text | 3 | ▲5.8%(up) | 74 | 2.6B |
| 21 | Wan2.2-TI2V-5B-GGUFQuantStack | Text to Video | 3 | ▲4.8%(up) | 240 | — |
| 22 | trocr-large-strmicrosoft | Image to Text | 3 | ▲0.5%(up) | 20 | — |
| 23 | GR00T-N1.7-SimplerEnv-Bridgenvidia | Robotics | 3 | ▲3.9%(up) | 8 | 3.1B |
| 24 | tipsv2-g14-dptgoogle | Depth Estimation | 3 | ▲9.6%(up) | 19 | 1.3B |
| 25 | git-basemicrosoft | Image to Text | 3 | ▲0.1%(up) | 114 | 177M |
| 26 | Phi-3.5-vision-instruct-onnxmicrosoft | — | 3 | — | 24 | — |
| 27 | llava-med-7b-deltamicrosoft | Text Generation | 3 | ▲0.8%(up) | 76 | — |
| 28 | vit_small_patch14_dinov2.lvd142mtimm | Image Feature Extraction | 3 | ▲5.3%(up) | 11 | 22.1M |
| 29 | git-base-cocomicrosoft | Image to Text | 3 | ▲0.3%(up) | 25 | — |
| 30 | Dayhoff-3b-GR-HMmicrosoft | Text Generation | 3 | — | 5 | 3B |
| 31 | GLM-5.3-Flash-NVFP4-Sparklocal-inference-lab | Text Generation | 3 | ▲48.9%(up) | 18 | 165B |
| 32 | Sakura-Qwen3.8-Flash-Next-Swift-2.5bit-352E-32GB-GGUFwebmp3 | Text Generation | 3 | — | 4 | — |
| 33 | Qwen3-8B-NVFP4nvidia | Text Generation | 3 | ▲4.3%(up) | 27 | 4.7B |
| 34 | CodeQwen1.5-7BQwen | Text Generation | 3 | ▲0.4%(up) | 109 | 7.3B |
| 35 | trocr-small-printedmicrosoft | Image to Text | 3 | ▲0.4%(up) | 55 | 61.4M |
| 36 | Intern-Decision-4Binternlm | Image Text to Text | 3 | — | 88 | 4.5B |
| 37 | ocr-captcha-v3anuashok | — | 3 | ▲2.1%(up) | 42 | 334M |
| 38 | Qwen-7B-Chat-Int4Qwen | Text Generation | 3 | ▲0.1%(up) | 78 | 7.7B |
| 39 | Qwen3-4B-AWQQwen | Text Generation | 3 | ▲2.2%(up) | 36 | 4B |
| 40 | FLUX.2-klein-base-4Bblack-forest-labs | Image To Image | 3 | ▲2.0%(up) | 184 | 3.9B |
| 41 | xdoc-base-squad2.0microsoft | Question Answering | 3 | — | 4 | — |
| 42 | Llama-3.2-11B-Vision-Instructmeta-llama | Image Text to Text | 3 | ▲0.1%(up) | 1,679 | 10.7B |
| 43 | MEXMAfacebook | Sentence Similarity | 3 | ▲0.5%(up) | 34 | 559M |
| 44 | microsoft_Phi-4-mini-instruct-GGUFbartowski | Text Generation | 3 | ▲4.8%(up) | 52 | — |
| 45 | Gemma-4-31B-Loki-Scotoma-V2.0-Swa-4096-GGUFCrucibleLab | — | 3 | ▲3.0%(up) | 8 | — |
| 46 | FrogMini-14B-2510microsoft | Text Generation | 3 | ▲1.8%(up) | 67 | 425K |
| 47 | C-RADIOv3-Lnvidia | — | 3 | ▲3.7%(up) | 8 | 320M |
| 48 | gemma-4-E4B-it-qat-w4a16-ctgoogle | Any to Any | 3 | ▲12.3%(up) | 26 | 8.6B |
| 49 | ALoDLM-1.7Bamazon | Text Generation | 3 | — | 11 | 2B |
| 50 | bigvgan_v2_24khz_100band_256xnvidia | Audio to Audio | 3 | ▲1.9%(up) | 28 | — |