| 1 | Qwen3.8-27B-GGUFbartowski | Image Text to Text | 3 | ▲47.3%(up) | 217 | — |
| 2 | SNOFSAshen3 | — | 3 | — | 104 | — |
| 3 | gpt-oss-safeguard-120bopenai | Text Generation | 3 | ▲0.2%(up) | 121 | 117B |
| 4 | RusMind-MomentumDICPlay | Text Generation | 3 | — | 8 | — |
| 5 | Spark-X2.5-4B-GGUFXHToken | Text Generation | 3 | ▲87.8%(up) | 283 | — |
| 6 | Qwen3.6-35B-A3B-2Bit-GSQ-hybrid-GGUFchtisgit | Image Text to Text | 3 | — | 11 | — |
| 7 | Dia-1.6Bnari-labs | Text to Speech | 3 | ▲0.4%(up) | 2,934 | 1.6B |
| 8 | Spark-X2.5-1.7BXHToken | Text Generation | 3 | ▲44.6%(up) | 155 | 1.7B |
| 9 | MagenticBrainmicrosoft | Text Generation | 3 | ▲8.6%(up) | 41 | 14.8B |
| 10 | GLM-5zai-org | Text Generation | 3 | ▲1.3%(up) | 2,139 | 754B |
| 11 | wmt19-en-defacebook | Translation | 3 | ▲0.1%(up) | 26 | 272M |
| 12 | Qwen2-72B-InstructQwen | Text Generation | 3 | ▲0.4%(up) | 724 | 72.7B |
| 13 | Hemmingway-1-Heretic-MTP-V3-VISION-Final-GGUFbrainnxdomain | — | 3 | — | 5 | — |
| 14 | parakeet-tdt_ctc-0.6b-janvidia | Speech Recognition | 3 | ▲0.4%(up) | 73 | — |
| 15 | gpt-oss-120b-Eagle3-long-contextnvidia | Text Generation | 3 | ▲0.4%(up) | 92 | 215M |
| 16 | Dayhoff-170M-GRS-2000microsoft | Text Generation | 3 | — | 6 | 170M |
| 17 | Qwen3Guard-Stream-4BQwen | Embeddings | 3 | ▲0.9%(up) | 39 | 4B |
| 18 | xdoc-base-squad1.1microsoft | Question Answering | 3 | — | 10 | — |
| 19 | xlm-mlm-17-1280FacebookAI | Fill Mask | 3 | ▲0.1%(up) | 9 | — |
| 20 | controlnet-openpose-sdxl-1.0xinsir | Text to Image | 3 | ▲2.1%(up) | 331 | 1.3B |
| 21 | FastVideo-FastH3-8-Step-V2-NVFP4-ComfyFastVideo | — | 3 | — | 10 | — |
| 22 | bitnet-embedding-270mmicrosoft | — | 3 | ▲12.0%(up) | 24 | — |
| 23 | gemma-4-E4B-it-qat-mobile-ctgoogle | Any to Any | 3 | ▲2.0%(up) | 35 | 8.7B |
| 24 | beit-large-patch16-512microsoft | Image Classification | 3 | ▲0.1%(up) | 21 | — |
| 25 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16nvidia | Text Generation | 3 | ▲1.5%(up) | 28 | 31.6B |
| 26 | CodeQwen1.5-7B-AWQQwen | Text Generation | 3 | ▲0.1%(up) | 10 | 7.3B |
| 27 | Qwen3.8-Flash-Next-NVFP4local-inference-lab | Image Text to Text | 3 | ▲141.5%(up) | 58 | 92.7B |
| 28 | efficientnet-b3google | Image Classification | 3 | ▲1.1%(up) | 17 | — |
| 29 | vit-large-patch32-384google | Image Classification | 3 | ▲0.1%(up) | 23 | — |
| 30 | deepseek-coder-33b-basedeepseek-ai | Text Generation | 3 | ▲0.3%(up) | 94 | 33.3B |
| 31 | Qwen3-4B-MLX-4bitQwen | Text Generation | 3 | ▲0.0%(up) | 41 | 4B |
| 32 | layoutlmv3-base-chinesemicrosoft | — | 3 | ▲0.6%(up) | 90 | — |
| 33 | Qwen3-235B-A22B-MLX-bf16Qwen | Text Generation | 3 | — | 13 | 235B |
| 34 | tipsv2-b14google | Zero-Shot Image Classification | 3 | ▲11.3%(up) | 134 | 196M |
| 35 | Qwen2.5-32B-Instruct-GPTQ-Int8Qwen | Text Generation | 3 | ▲0.1%(up) | 22 | 32.8B |
| 36 | plamo-2-translatepfnet | Translation | 3 | ▲0.3%(up) | 128 | 9.5B |
| 37 | Huihui-Qwen3.5-9B-abliteratedhuihui-ai | Image Text to Text | 3 | ▲1.0%(up) | 157 | 9.7B |
| 38 | Qwen2.5-Coder-3B-Instruct-GPTQ-Int8Qwen | Text Generation | 3 | — | 7 | 3.1B |
| 39 | Qwen3-VL-4B-ThinkingQwen | Image Text to Text | 3 | ▲0.6%(up) | 131 | 4.4B |
| 40 | Qwen3-1.7B-MLX-bf16Qwen | Text Generation | 3 | 0% | 13 | 1.7B |
| 41 | xlm-clm-ende-1024FacebookAI | Fill Mask | 3 | ▲0.0%(up) | 5 | 209M |
| 42 | SkinTokensVAST-AI | — | 3 | — | 45 | — |
| 43 | git-base-vqav2microsoft | Visual Question Answering | 3 | — | 26 | 177M |
| 44 | pegasus-largegoogle | Summarization | 3 | ▲0.1%(up) | 115 | — |
| 45 | Qwen2-7B-Instruct-GPTQ-Int8Qwen | Text Generation | 3 | — | 24 | 7.6B |
| 46 | Qwen-Image-Edit-2511-Lightninglightx2v | Image To Image | 3 | ▲3.1%(up) | 541 | — |
| 47 | t5-3b-ssm-nqgoogle | Text Generation | 3 | — | 6 | — |
| 48 | WanVideo_comfy_fp8_scaledKijai | — | 3 | ▲1.4%(up) | 752 | — |
| 49 | Qwen3-0.6B-MLX-8bitQwen | Text Generation | 3 | — | 10 | 596M |
| 50 | MiniCPM-Llama3-V-2_5openbmb | Image Text to Text | 3 | ▲0.5%(up) | 1,422 | 8.5B |