| 1 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4nvidia | Text Generation | 135.8K | +135.8K | 445 | 17.8B |
| 2 | distil-large-v3distil-whisper | Speech Recognition | 135.8K | +135.8K | 383 | 756M |
| 3 | open-vakgyataonecxi | Audio Classification | 135.3K | +135.3K | 3 | 58.7M |
| 4 | wav2vec2-large-xls-r-300m-welshinfinitejoy | Speech Recognition | 135.2K | +135.2K | 1 | — |
| 5 | gemma-4-31B-it-qat-GGUFunsloth | Image Text to Text | 135.2K | +135.2K | 202 | — |
| 6 | inclusively-classificationE-MIMIC | Text Classification | 135K | +135K | 1 | 111M |
| 7 | Qwen_Qwen3.5-27B-GGUFbartowski | Image Text to Text | 134.8K | +134.8K | 76 | — |
| 8 | Voxtral-Mini-4B-Realtime-2602mistralai | Speech Recognition | 134.6K | +134.6K | 998 | 4.4B |
| 9 | ms-marco-MiniLM-L-6-v2Xenova | Text Classification | 134K | +134K | 10 | — |
| 10 | bert-base-arabertv02aubmindlab | Fill Mask | 133.7K | +133.7K | 51 | 136M |
| 11 | Qwen3.8-27B-NVFP4-RTX5090gittensor-model-hub | Image Text to Text | 133.3K | +133.3K | 171 | 14.6B |
| 12 | parakeet-tdt-0.6b-v3nvidia | Speech Recognition | 133.2K | +133.2K | 1,172 | 627M |
| 13 | SeedVR2_comfyUInumz | Video To Video | 133.1K | +133.1K | 326 | — |
| 14 | LFM2.5-230M-GGUFLiquidAI | Text Generation | 133K | +133K | 111 | — |
| 15 | granite-4.1-3bibm-granite | Text Generation | 133K | +133K | 113 | 3.4B |
| 16 | xlm-roberta_punctuation_fullstop_truecase1-800-BAD-CODE | — | 132.6K | +132.6K | 70 | — |
| 17 | tiny-GptOssForCausalLMtrl-internal-testing | Text Generation | 132.6K | +132.6K | 4 | 3.2M |
| 18 | LTX-2.3-fp8Lightricks | Image To Video | 132.6K | +132.6K | 141 | — |
| 19 | HunyuanVideo_1.5_repackagedComfy-Org | — | 132.5K | +132.5K | 101 | — |
| 20 | tiny-random-gpt2optimum-intel-internal-testing | — | 132.4K | +132.4K | 0 | 112K |
| 21 | Bonsai-27B-ggufprism-ml | Text Generation | 132.2K | +132.2K | 885 | — |
| 22 | ModernBERT-largeanswerdotai | Fill Mask | 132K | +132K | 496 | 396M |
| 23 | macbert4csc-base-chineseshibing624 | Text Generation | 132K | +132K | 121 | 102M |
| 24 | table-transformer-detectionmicrosoft | Object Detection | 131.8K | +131.8K | 431 | 28.8M |
| 25 | Qwen3-Omni-30B-A3B-InstructQwen | Any to Any | 131.4K | +131.4K | 1,012 | 35.3B |
| 26 | gemma-4-26B-A4B-it-qat-q4_0-ggufgoogle | Image Text to Text | 131.3K | +131.3K | 177 | — |
| 27 | nemotron-speech-streaming-en-0.6bnvidia | Speech Recognition | 131.3K | +131.3K | 632 | 618M |
| 28 | Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16nvidia | Any to Any | 131.2K | +131.2K | 436 | 33B |
| 29 | bert-base-german-caseddbmdz | Fill Mask | 131K | +131K | 27 | 111M |
| 30 | Qwen2.5-7BQwen | Text Generation | 130.7K | +130.7K | 323 | 7.6B |
| 31 | vae-text-encorder-for-flux-klein-4bComfy-Org | — | 130.5K | +130.5K | 99 | — |
| 32 | marlin-2b-ggufjadeonrails | — | 130.4K | +130.4K | 1 | — |
| 33 | caduceus-ps_seqlen-131k_d_model-256_n_layer-16kuleshov-group | Fill Mask | 130.4K | +130.4K | 14 | 7.7M |
| 34 | Qwen3.8-4B-Distill-GGUFempero-ai | Text Generation | 130.3K | +130.3K | 163 | — |
| 35 | tiny-Qwen2_5_VLForConditionalGenerationtrl-internal-testing | Image Text to Text | 130.3K | +130.3K | 0 | 3.9M |
| 36 | Z-Image-TurboTongyi-MAI | Text to Image | 130K | +130K | 5,402 | 6.2B |
| 37 | robertuito-sentiment-analysispysentimiento | Text Classification | 129.7K | +129.7K | 107 | 109M |
| 38 | PE-Core-L14-336facebook | Zero-Shot Image Classification | 129.1K | +129.1K | 57 | — |
| 39 | Qwen3.8-Flash-NextQwen | Image Text to Text | 128.9K | +128.9K | 5,860 | 180B |
| 40 | Spark-X2.5-4B-GGUFXHToken | Text Generation | 128.5K | +128.5K | 260 | — |
| 41 | whisper-bemba-sttAbelZimba | Speech Recognition | 128K | +128K | 0 | 242M |
| 42 | Swift-Qwen3.8-27B-GGUFukisai | Image Text to Text | 127.7K | +127.7K | 449 | — |
| 43 | Kronos-miniNeoQuasar | Time Series Forecasting | 127.7K | +127.7K | 33 | 4.1M |
| 44 | UI-TARS-1.5-7BByteDance-Seed | Image Text to Text | 127.5K | +127.5K | 607 | 8.3B |
| 45 | Llama-3.2-3B-Instruct-FP8-dynamicRedHatAI | Text Generation | 127.5K | +127.5K | 3 | 3.6B |
| 46 | tiny-random-Llama-3llamafactory | Text Generation | 127.4K | +127.4K | 4 | 4.1M |
| 47 | gpt-neo-125mEleutherAI | Text Generation | 127.3K | +127.3K | 230 | 150M |
| 48 | Minimax-h3_SingularityWarmBloodAban | Image To Video | 127.2K | +127.2K | 718 | — |
| 49 | gemma-3-27b-itgoogle | Image Text to Text | 127K | +127K | 2,045 | 27.4B |
| 50 | LTX-VideoLightricks | Image To Video | 127K | +127K | 2,324 | 1.9B |