| 1 | Vela-1.0-Omni-Nanovllm-sr | Embeddings | 2 | — | 5 | 164M |
| 2 | Qwopus3-5-9B-Coder-Flash-i1-GGUFmradermacher | — | 2 | — | 2 | — |
| 3 | roberta2roberta_L-24_discofusegoogle | — | 2 | — | 4 | — |
| 4 | t5-efficient-base-el4google | — | 2 | — | 3 | — |
| 5 | Qwen3-TTS-12Hz-1.7B-Base-GGUFNANI-Nithin | Text to Speech | 2 | — | 3 | — |
| 6 | clef-flash-hereticsaidutta69 | Image Text to Text | 2 | — | 2 | 9.4B |
| 7 | Depth-Anything-3Comfy-Org | — | 2 | ▲19.4%(up) | 25 | — |
| 8 | Step-Audio-EditXstepfun-ai | — | 2 | ▲0.5%(up) | 146 | 3.5B |
| 9 | Huihui-Qwen3.8-Flash-Next-abliterated-exl3-4bit-hq_h6_ng6alesha-pro | Image Text to Text | 2 | — | 6 | 34.1B |
| 10 | mms-tts-ayrfacebook | Text to Speech | 2 | — | 3 | 36.3M |
| 11 | Qwen3.6-35B-A3B-Westernizedhirundo-io | Image Text to Text | 2 | — | 2 | 36B |
| 12 | mms-tts-bulfacebook | Text to Speech | 2 | ▲1.6%(up) | 3 | 36.3M |
| 13 | Qwen3-Omni-30B-A3B-Thinking-heretic-GGUFmradermacher | — | 2 | ▲2.5%(up) | 4 | — |
| 14 | ReaderLM-v2-ParetrixSoulfate24 | Text Generation | 2 | — | 2 | — |
| 15 | mms-tts-shnfacebook | Text to Speech | 2 | 0% | 5 | 36.3M |
| 16 | mms-tts-marfacebook | Text to Speech | 2 | ▲1.8%(up) | 6 | 36.3M |
| 17 | vit-base-patch16-384google | Image Classification | 2 | ▲0.1%(up) | 54 | 86.9M |
| 18 | Iris-mini-MTP-APEX-I-MiniPlus-GGUFIsValorum | Text Generation | 2 | — | 2 | — |
| 19 | mms-tts-azj-script_latinfacebook | Text to Speech | 2 | 0% | 3 | 36.3M |
| 20 | JEV-27B-VL-GGUFAtlas3D | Image Text to Text | 2 | — | 9 | — |
| 21 | deit-tiny-patch16-224facebook | Image Classification | 2 | ▲4.2%(up) | 18 | — |
| 22 | Lythri-7B-A4B-Q4_0_8-GGUFLythri | Text Generation | 2 | — | 3 | — |
| 23 | t5-efficient-base-dm2000google | — | 2 | — | 3 | — |
| 24 | t5-efficient-small-el16-dl1google | — | 2 | — | 2 | — |
| 25 | t5-efficient-xlgoogle | — | 2 | — | 3 | — |
| 26 | Llama3-ChatQA-2-8Bnvidia | Text Generation | 2 | — | 20 | — |
| 27 | Qwen2.5-VL-7B-Surg-CholecT50nvidia | Image Text to Text | 2 | — | 13 | 8.3B |
| 28 | Dayhoff-170M-GRS-26000microsoft | Text Generation | 2 | — | 3 | 170M |
| 29 | DeepSeek-V4.1-Flash-LSQ3-G128-MLXgnahzhang | Text Generation | 2 | — | 2 | 763B |
| 30 | Qwen3.8-Flash-Next-Uncensored-NVFP4mazinb | Image Text to Text | 2 | ▲15.3%(up) | 36 | 120B |
| 31 | Qwen3.5-Fable5.1Hob-forge | Text Generation | 2 | — | 5 | — |
| 32 | bert_uncased_L-10_H-128_A-2google | — | 2 | — | 2 | — |
| 33 | DeepSeek-R1-NVFP4-v2nvidia | Text Generation | 2 | — | 10 | 394B |
| 34 | Consistance_Edit_Loralrzjason | — | 2 | — | 203 | — |
| 35 | content-type-classifier-debertanvidia | — | 2 | — | 21 | 184M |
| 36 | Qwythos-27B-v1-GGUFempero-ai | Image Text to Text | 2 | ▲14.1%(up) | 75 | — |
| 37 | git-large-rmicrosoft | Image to Text | 2 | — | 5 | 394M |
| 38 | xlm-roberta-xlfacebook | Fill Mask | 2 | ▲1.2%(up) | 37 | 3.5B |
| 39 | AesCode-32B-GGUFmradermacher | Reinforcement Learning | 2 | — | 2 | — |
| 40 | parakeet-rnnt-1.1bnvidia | Speech Recognition | 2 | ▲0.0%(up) | 187 | 1.1B |
| 41 | mobilenet_v2_1.4_224google | Image Classification | 2 | ▲0.8%(up) | 6 | — |
| 42 | StreamRender-H3Efficient-Large-Model | — | 2 | — | 4 | — |
| 43 | camie-tagger-v2Camais03 | Image Classification | 2 | ▲1.9%(up) | 85 | — |
| 44 | CoER-AttackerZ-Edgar | Text Generation | 2 | — | 2 | 9B |
| 45 | jpt-9bkirp | Image Text to Text | 2 | — | 6 | 9.4B |
| 46 | Qwen3-Omni-30B-A3B-Instruct-AWQ-4bitcyankiwi | Any to Any | 2 | ▲0.8%(up) | 63 | 10B |
| 47 | stt_ar_fastconformer_hybrid_large_pc_v1.0nvidia | Speech Recognition | 2 | ▲0.1%(up) | 21 | — |
| 48 | Foundation-1RoyalCities | — | 2 | — | 376 | — |
| 49 | Triumvirate-GGUFpragmaticcs | Text Generation | 2 | — | 2 | — |
| 50 | GLM-5.3-Mixed346-GPTQ-H32-A8-g128HawkBearPig | Text Generation | 2 | — | 2 | 106B |