| 1 |
Comfy-Org/MiniMax-H3 |
740,372.1 |
92.1 |
other |
| 2 |
farbodtavakkoli/OTel-2.0-LLM-31B-IT |
226,313.1 |
0.5 |
text-generation |
| 3 |
sentence-transformers/all-MiniLM-L6-v2 |
153,684.6 |
3.2 |
sentence-similarity |
| 4 |
nvidia/Qwen3.6-35B-A3B-NVFP4 |
144,399.8 |
7.0 |
text-generation |
| 5 |
amazon/chronos-2 |
123,763.2 |
1.4 |
time-series-forecasting |
| 6 |
unsloth/Muse-Glimmer-30B-GGUF |
117,341.0 |
130.0 |
image-text-to-text |
| 7 |
deepseek-ai/DeepSeek-V4-Flash-0731 |
110,122.1 |
255.3 |
text-generation |
| 8 |
MiniMaxAI/MiniMax-H3 |
100,371.2 |
238.7 |
image-text-to-video |
| 9 |
DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF |
99,754.1 |
71.0 |
image-text-to-text |
| 10 |
ornith-ai/Ornith-1.0-9B-GGUF |
93,771.8 |
13.0 |
text-generation |
| 11 |
Qwen/Qwen3.6-35B-A3B-FP8 |
88,752.1 |
2.9 |
image-text-to-text |
| 12 |
Qwen/Qwen3.5-9B |
81,337.6 |
10.8 |
image-text-to-text |
| 13 |
google-bert/bert-base-uncased |
70,634.8 |
1.7 |
fill-mask |
| 14 |
ornith-ai/Ornith-1.0-35B-GGUF |
70,132.3 |
21.1 |
text-generation |
| 15 |
Abiray/Minimax-H3-nvfp4-INT4-INT8-Convrot |
66,110.1 |
17.8 |
image-text-to-video |
| 16 |
google/gemma-4-26B-A4B-it |
64,993.7 |
8.9 |
image-text-to-text |
| 17 |
prism-ml/Bonsai-27B-gguf |
64,572.5 |
18.9 |
text-generation |
| 18 |
google/gemma-4-31B-it |
63,972.3 |
22.9 |
image-text-to-text |
| 19 |
Qwen/Qwen3-0.6B |
61,137.8 |
3.2 |
text-generation |
| 20 |
Abiray/MiniMax-H3-GGUF |
60,632.3 |
10.2 |
image-to-video |
| 21 |
Qwen/Qwen3.6-27B |
59,917.7 |
19.8 |
image-text-to-text |
| 22 |
ornith-ai/Ornith-1.0-35B |
54,144.1 |
9.2 |
text-generation |
| 23 |
baidu/Unlimited-OCR |
52,373.7 |
73.5 |
image-text-to-text |
| 24 |
Qwen/Qwen3.6-35B-A3B |
46,749.8 |
22.3 |
image-text-to-text |
| 25 |
zai-org/GLM-5.2 |
45,902.2 |
85.3 |
text-generation |
| 26 |
ornith-ai/Ornith-1.0-9B |
44,979.9 |
10.0 |
text-generation |
| 27 |
Qwen/Qwen3.5-4B |
43,870.0 |
4.9 |
image-text-to-text |
| 28 |
google/gemma-4-12B-it |
39,170.5 |
17.5 |
any-to-any |
| 29 |
BAAI/bge-m3 |
36,721.6 |
3.7 |
sentence-similarity |
| 30 |
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 |
34,662.2 |
0.8 |
sentence-similarity |
| 31 |
lmstudio-community/Muse-Glimmer-30B-GGUF |
34,491.3 |
3.0 |
other |
| 32 |
google/gemma-4-E4B-it |
31,203.2 |
9.0 |
any-to-any |
| 33 |
realrebelai/MiniMax-H3_GGUFs |
27,529.9 |
19.9 |
other |
| 34 |
DeepBeepMeep/MiniMax-H3 |
24,723.7 |
4.0 |
other |
| 35 |
google/gemma-4-E2B-it |
23,685.9 |
5.4 |
any-to-any |
| 36 |
google/gemma-4-12B-it-qat-w4a16-ct |
23,533.9 |
0.8 |
any-to-any |
| 37 |
Abiray/MiniMax-H3-Pruned-GGUF |
21,771.3 |
6.8 |
image-text-to-video |
| 38 |
Comfy-Org/z_image_turbo |
21,077.4 |
3.1 |
other |
| 39 |
unsloth/DeepSeek-V4-Flash-0731-GGUF |
20,674.0 |
51.7 |
other |
| 40 |
BAAI/bge-reranker-v2-m3 |
20,625.4 |
1.3 |
text-classification |
| 41 |
hexgrad/Kokoro-82M |
19,673.0 |
11.2 |
text-to-speech |
| 42 |
Qwen/Qwen3-ASR-1.7B |
19,619.1 |
5.1 |
automatic-speech-recognition |
| 43 |
Qwen/Qwen3-Embedding-0.6B |
18,541.8 |
2.6 |
feature-extraction |
| 44 |
unsloth/MiniMax-H3-GGUF |
18,537.0 |
24.8 |
image-text-to-video |
| 45 |
nomic-ai/nomic-embed-text-v1.5 |
16,790.1 |
1.0 |
sentence-similarity |
| 46 |
molbal/MiniMax-H3-GGUF |
16,607.3 |
4.9 |
image-to-video |
| 47 |
lightx2v/Minimax-h3-Turbo |
15,242.5 |
76.8 |
image-to-video |
| 48 |
nvidia/Nemotron-3-Embed-1B-BF16 |
15,234.1 |
4.5 |
sentence-similarity |
| 49 |
mudler/KAT-Coder-V2.5-Dev-APEX-GGUF |
15,002.1 |
2.1 |
other |
| 50 |
Qwen/Qwen3-TTS-12Hz-1.7B-Base |
14,219.1 |
2.4 |
other |
| 51 |
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4 |
12,817.5 |
1.6 |
any-to-any |
| 52 |
openai/clip-vit-base-patch32 |
12,632.1 |
0.6 |
zero-shot-image-classification |
| 53 |
Comfy-Org/Wan_2.2_ComfyUI_Repackaged |
12,375.8 |
2.2 |
other |
| 54 |
deepgrove/maple-preview-GGUF |
12,001.4 |
7.6 |
other |
| 55 |
nvidia/nemotron-3.5-asr-streaming-0.6b |
11,865.7 |
11.5 |
automatic-speech-recognition |
| 56 |
openai/whisper-large-v3-turbo |
11,434.1 |
4.8 |
automatic-speech-recognition |
| 57 |
pyannote/speaker-diarization-community-1 |
11,025.3 |
2.1 |
automatic-speech-recognition |
| 58 |
FacebookAI/xlm-roberta-base |
10,783.9 |
0.5 |
fill-mask |
| 59 |
mistralai/Voxtral-Mini-4B-Realtime-2602 |
10,732.2 |
4.6 |
automatic-speech-recognition |
| 60 |
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice |
10,584.3 |
9.2 |
text-to-speech |
| 61 |
Lightricks/LTX-2.3 |
10,382.4 |
11.2 |
image-to-video |
| 62 |
joeygambino/MiniMax-H3-encoder-GGUF |
9,334.7 |
0.7 |
image-to-video |
| 63 |
pyannote/speaker-diarization-3.1 |
8,864.4 |
3.1 |
automatic-speech-recognition |
| 64 |
coqui/XTTS-v2 |
8,379.0 |
3.7 |
text-to-speech |
| 65 |
facebook/sam3 |
8,036.5 |
9.5 |
mask-generation |
| 66 |
Qwen/Qwen3-Embedding-8B |
6,489.8 |
1.8 |
feature-extraction |
| 67 |
google/embeddinggemma-300m |
6,185.0 |
4.7 |
sentence-similarity |
| 68 |
CohereLabs/cohere-transcribe-03-2026 |
6,115.4 |
7.6 |
automatic-speech-recognition |
| 69 |
k2-fsa/OmniVoice |
6,026.7 |
9.3 |
text-to-speech |
| 70 |
google/gemma-4-12B-it-qat-q4_0-gguf |
5,933.4 |
3.8 |
any-to-any |
| 71 |
pyannote/segmentation-3.0 |
5,780.1 |
1.4 |
voice-activity-detection |
| 72 |
meta-llama/Prompt-Guard-86M |
5,778.5 |
0.5 |
text-classification |
| 73 |
vantagewithai/MiniMax-H3-comfyUI-GGUF |
5,672.9 |
1.8 |
image-text-to-video |
| 74 |
microsoft/TRELLIS.2-4B |
5,062.7 |
4.3 |
image-to-3d |
| 75 |
unsloth/gemma-4-12B-it-qat-GGUF |
5,035.3 |
6.0 |
any-to-any |
| 76 |
openbmb/MiniCPM-o-4_5 |
4,942.0 |
7.7 |
any-to-any |
| 77 |
openai/whisper-large-v3 |
4,904.3 |
6.1 |
automatic-speech-recognition |
| 78 |
Lightricks/LTX-2.3-fp8 |
4,783.9 |
0.8 |
image-to-video |
| 79 |
rockerBOO/minimax-h3-nvfp4-convrot |
4,424.1 |
2.2 |
text-to-video |
| 80 |
audio-cpp/audio.cpp-gguf |
4,367.2 |
1.7 |
text-to-speech |
| 81 |
ResembleAI/chatterbox |
4,345.0 |
3.6 |
text-to-speech |
| 82 |
openbmb/VoxCPM2 |
4,243.0 |
11.6 |
text-to-speech |
| 83 |
black-forest-labs/FLUX.2-dev |
4,044.5 |
7.6 |
image-to-image |
| 84 |
openai/privacy-filter |
3,850.0 |
14.6 |
token-classification |
| 85 |
bosonai/higgs-tts-3-4b |
3,634.6 |
10.1 |
text-to-speech |
| 86 |
Tongyi-MAI/Z-Image-Turbo |
3,603.1 |
19.6 |
text-to-image |
| 87 |
SulphurAI/Sulphur-2-base |
3,464.1 |
19.5 |
text-to-video |
| 88 |
Qwen/Qwen3-Omni-30B-A3B-Instruct |
3,355.9 |
3.0 |
any-to-any |
| 89 |
microsoft/VibeVoice-ASR |
3,263.0 |
6.2 |
automatic-speech-recognition |
| 90 |
fishaudio/s2-pro |
3,192.8 |
7.9 |
text-to-speech |
| 91 |
NeoQuasar/Kronos-base |
3,116.1 |
0.6 |
time-series-forecasting |
| 92 |
Qwen/Qwen3-ASR-0.6B-hf |
3,112.4 |
1.2 |
automatic-speech-recognition |
| 93 |
onnx-community/Kokoro-82M-v1.0-ONNX |
2,882.1 |
0.4 |
text-to-speech |
| 94 |
unsloth/gemma-4-E2B-it-qat-GGUF |
2,847.7 |
1.0 |
any-to-any |
| 95 |
ProsusAI/finbert |
2,744.1 |
0.7 |
text-classification |
| 96 |
Lightricks/LTX-2.5 |
2,728.0 |
34.2 |
image-to-video |
| 97 |
Qwen/Qwen3-ForcedAligner-0.6B-hf |
2,452.8 |
0.5 |
token-classification |
| 98 |
CornLogic/10EROS-INT8 |
2,255.6 |
1.3 |
image-to-video |
| 99 |
OpenMOSS-Team/MOSS-Transcribe-Diarize |
2,223.0 |
4.4 |
audio-text-to-text |
| 100 |
Abiray/10Eros-Max-GGUF |
2,138.3 |
5.3 |
image-text-to-video |
| 101 |
stable-diffusion-v1-5/stable-diffusion-v1-5 |
2,063.2 |
1.7 |
text-to-image |
| 102 |
facebook/dinov2-base |
2,030.6 |
0.2 |
image-feature-extraction |
| 103 |
facebook/dinov3-vitl16-pretrain-lvd1689m |
1,833.7 |
1.4 |
image-feature-extraction |
| 104 |
google/siglip2-base-patch16-224 |
1,825.1 |
0.2 |
zero-shot-image-classification |
| 105 |
zeroentropy/zerank-2-reranker |
1,819.5 |
0.4 |
text-ranking |
| 106 |
krea/Krea-2-Raw |
1,808.0 |
8.6 |
text-to-image |
| 107 |
black-forest-labs/FLUX.2-klein-4B |
1,768.5 |
4.0 |
image-to-image |
| 108 |
numind/NuExtract3 |
1,638.8 |
3.1 |
image-to-text |
| 109 |
WarmBloodAban/Krea2_Anything2RealCharacters-V2 |
1,638.1 |
3.0 |
image-to-image |
| 110 |
facebook/dinov3-vitb16-pretrain-lvd1689m |
1,636.1 |
0.6 |
image-feature-extraction |
| 111 |
Abiray/MiniMax-H3-Turbo-Lora-Pruned-ComfyUI |
1,610.0 |
5.9 |
image-text-to-video |
| 112 |
fal/MiniMax-H3-Realism-People-LoRA |
1,564.0 |
52.3 |
image-text-to-video |
| 113 |
krea/Krea-2-Turbo |
1,559.8 |
15.3 |
text-to-image |
| 114 |
black-forest-labs/FLUX.2-klein-9B |
1,472.5 |
5.7 |
image-to-image |
| 115 |
bench-labs/PixelModel-v6 |
1,448.9 |
2.0 |
text-to-image |
| 116 |
unsloth/LTX-2.3-GGUF |
1,376.8 |
3.4 |
image-to-video |
| 117 |
jhu-clsp/mmBERT-base |
1,372.0 |
0.6 |
fill-mask |
| 118 |
Qwen/Qwen-Image-Edit-2509 |
1,324.3 |
3.8 |
image-to-image |
| 119 |
stabilityai/sdxl-turbo |
1,319.7 |
2.6 |
text-to-image |
| 120 |
stabilityai/stable-diffusion-xl-base-1.0 |
1,302.5 |
7.2 |
text-to-image |
| 121 |
lightx2v/Qwen-Image-Edit-2511-Lightning |
1,265.3 |
2.2 |
image-to-image |
| 122 |
kyutai/mimi |
1,114.4 |
0.5 |
feature-extraction |
| 123 |
facebook/dinov3-vits16-pretrain-lvd1689m |
1,110.1 |
0.4 |
image-feature-extraction |
| 124 |
livekit/turn-detector |
995.1 |
0.2 |
text-classification |
| 125 |
briaai/RMBG-2.0 |
975.6 |
2.1 |
image-segmentation |
| 126 |
AlperKTS/Krea2_FP8 |
971.7 |
2.0 |
text-to-image |
| 127 |
nvidia/personaplex-7b-v1 |
967.5 |
11.8 |
audio-to-audio |
| 128 |
ZhengPeng7/BiRefNet |
955.1 |
0.8 |
image-segmentation |
| 129 |
vantagewithai/Krea-2-Turbo-GGUF |
952.5 |
2.5 |
text-to-image |
| 130 |
unsloth/Qwen-Image-Edit-2511-GGUF |
918.6 |
2.4 |
image-to-image |
| 131 |
microsoft/resnet-50 |
914.4 |
0.3 |
image-classification |
| 132 |
wikeeyang/Krea2-Turbo-HD-V1 |
868.7 |
2.3 |
text-to-image |
| 133 |
google/tabfm-1.0.0-pytorch |
852.5 |
10.1 |
tabular-classification |
| 134 |
Lightricks/LTX-Video |
848.8 |
3.5 |
image-to-video |
| 135 |
NeoQuasar/Kronos-Tokenizer-2k |
827.6 |
0.0 |
time-series-forecasting |
| 136 |
unsloth/FLUX.2-klein-4B-GGUF |
819.8 |
0.9 |
image-to-image |
| 137 |
Qwen/Qwen-Image-Edit-2511 |
805.7 |
5.3 |
image-to-image |
| 138 |
facebook/sam3.1 |
568.8 |
3.7 |
mask-generation |
| 139 |
numz/SeedVR2_comfyUI |
547.9 |
0.7 |
video-to-video |
| 140 |
black-forest-labs/FLUX.1-Kontext-dev |
522.5 |
6.3 |
image-to-image |
| 141 |
Wan-AI/Wan2.2-TI2V-5B-Diffusers |
498.1 |
0.4 |
text-to-video |
| 142 |
stabilityai/stable-audio-3-medium |
421.5 |
3.0 |
text-to-audio |
| 143 |
Novice25/Qwen-Image-Edit-Rapid-AIO-GGUF |
402.6 |
1.0 |
image-text-to-image |
| 144 |
ddalcu/MiniMax-H3-FL2VA-MLX-Serve-8bit |
345.0 |
1.4 |
text-to-video |
| 145 |
nvidia/GR00T-N1.7-3B |
285.9 |
0.6 |
robotics |
| 146 |
ACE-Step/Ace-Step1.5 |
280.1 |
4.1 |
text-to-audio |
| 147 |
bosonai/higgs-audio-v2-tokenizer |
278.9 |
0.1 |
feature-extraction |
| 148 |
meta-llama/Llama-Prompt-Guard-2-86M |
256.9 |
0.4 |
text-classification |
| 149 |
google/madlad400-3b-mt |
232.4 |
0.2 |
translation |
| 150 |
ChrisColeTech/minimax-h3-turbo-GGUF |
214.0 |
3.0 |
text-to-video |
| 151 |
MahmoodLab/UNI |
175.7 |
0.4 |
image-feature-extraction |
| 152 |
hotchpotch/bekko-embedding-v1-a25m |
163.7 |
0.5 |
sentence-similarity |
| 153 |
AInVFX/SeedVR2_comfyUI |
156.1 |
0.2 |
video-to-video |
| 154 |
Lightricks/LTX-2.3-22b-IC-LoRA-Ingredients |
151.9 |
3.1 |
video-to-video |
| 155 |
nvidia/RE-USE |
151.2 |
0.6 |
audio-to-audio |
| 156 |
nomic-ai/nomic-embed-text-v1.5-GGUF |
135.0 |
0.1 |
sentence-similarity |
| 157 |
tencent/Hunyuan3D-2.1 |
128.5 |
2.6 |
image-to-3d |
| 158 |
nationaldesignstudio/rampart |
128.4 |
3.5 |
token-classification |
| 159 |
nvidia/Alpamayo2-Super |
123.1 |
1.3 |
robotics |
| 160 |
stabilityai/stable-fast-3d |
118.6 |
1.2 |
image-to-3d |
| 161 |
Prior-Labs/tabpfn_3 |
114.4 |
2.0 |
tabular-classification |
| 162 |
Wan-AI/Wan2.1-T2V-1.3B |
94.6 |
0.9 |
text-to-video |
| 163 |
human-centered-summarization/financial-summarization-pegasus |
93.5 |
0.1 |
summarization |
| 164 |
lightonai/mLateOn |
91.1 |
0.4 |
sentence-similarity |
| 165 |
LiquidAI/LFM2.5-Encoder-350M-Prompt-Router |
84.6 |
1.7 |
text-classification |
| 166 |
Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler |
80.5 |
13.0 |
video-to-video |
| 167 |
HiDream-ai/HiDream-O1-Image |
76.8 |
5.4 |
image-text-to-image |
| 168 |
realrebelai/LTX-2.5_GGUFs |
76.0 |
5.0 |
text-to-video |
| 169 |
speechbrain/lang-id-voxlingua107-ecapa |
75.8 |
0.1 |
audio-classification |
| 170 |
PramaLLC/BEN2 |
75.0 |
0.4 |
image-segmentation |
| 171 |
JustANormalTinkerer/hayai-ocr-v2 |
72.0 |
2.5 |
image-to-text |
| 172 |
NemoStation/Marlin-2B |
71.9 |
6.3 |
video-text-to-text |
| 173 |
Wan-AI/Wan2.2-Animate-14B |
59.2 |
3.7 |
video-to-video |
| 174 |
lerobot/pi05_base |
57.5 |
0.3 |
robotics |
| 175 |
Wan-AI/Wan2.1-T2V-14B |
47.1 |
2.9 |
text-to-video |
| 176 |
Ultralytics/YOLO26 |
44.5 |
0.7 |
object-detection |
| 177 |
LiquidAI/LFM2.5-Encoder-350M-PII-Detector |
41.2 |
0.5 |
token-classification |
| 178 |
SexGod1979/PinkCherry_MiniMax-H3 |
40.5 |
37.2 |
text-to-video |
| 179 |
NovaSearch/stella_en_1.5B_v5 |
38.8 |
0.3 |
sentence-similarity |
| 180 |
Wan-AI/Wan2.2-TI2V-5B |
31.5 |
1.9 |
text-to-video |
| 181 |
nvidia/gliner-PII |
26.1 |
0.4 |
token-classification |
| 182 |
unsloth/MiniMax-H3 |
24.2 |
3.2 |
image-text-to-video |
| 183 |
stabilityai/stable-audio-open-1.0 |
24.0 |
1.9 |
text-to-audio |
| 184 |
LG-AI-Research/EXAONE-Tabular |
24.0 |
0.5 |
tabular-classification |
| 185 |
Merserk/MiniMax-H3-INT4-ConvRot |
23.9 |
2.9 |
image-text-to-video |
| 186 |
aufklarer/VoiceChat-11B-Perception-MLX-int5 |
18.1 |
0.7 |
audio-to-audio |
| 187 |
tiiuae/Falcon-OCR |
17.4 |
0.8 |
image-to-text |
| 188 |
tencent/HunyuanWorld-Mirror |
16.6 |
1.5 |
image-to-3d |
| 189 |
bench-labs/AudioModel-v1 |
14.0 |
2.5 |
text-to-audio |
| 190 |
Alibaba-DAMO-Academy/RynnValue-8B |
12.6 |
0.2 |
robotics |
| 191 |
Ultralytics/YOLOv8 |
10.6 |
0.4 |
object-detection |
| 192 |
ProCreations/auto-0.4b |
10.4 |
1.4 |
text-classification |
| 193 |
dima806/deepfake_vs_real_image_detection |
9.3 |
0.1 |
image-classification |
| 194 |
xiaomi-research/MiLMMT-46-1B-v1.0 |
8.6 |
2.1 |
translation |
| 195 |
jdopensource/JoyAI-Video-Edit |
7.3 |
6.3 |
video-to-video |
| 196 |
ProCreations/auto-1b |
7.2 |
1.2 |
text-classification |
| 197 |
kcz358/aero-realtime-4B |
6.3 |
0.9 |
video-text-to-text |
| 198 |
xiaomi-research/MiLMMT-46-4B-v1.0 |
6.1 |
2.0 |
translation |
| 199 |
xiaomi-research/MiLMMT-46-12B-v1.0 |
6.1 |
0.8 |
translation |
| 200 |
LiquidAI/LFM2.5-Audio-1.5B |
5.2 |
1.9 |
audio-to-audio |
| 201 |
Aignostics/RudolfV-2 |
4.8 |
0.6 |
image-feature-extraction |
| 202 |
MiniMaxAI/MiniMax-Music3 |
4.2 |
49.8 |
text-to-audio |
| 203 |
dronefreak/seadronessee-rfdetr-small |
4.0 |
2.0 |
object-detection |
| 204 |
TobiasLogic/chessmamba |
2.6 |
1.4 |
reinforcement-learning |
| 205 |
cisco-ai/stupase |
2.3 |
0.3 |
audio-to-audio |
| 206 |
OpenMOSS-Team/MOSS-VL-Instruct-0708-FP8 |
1.0 |
2.7 |
video-text-to-text |
| 207 |
gtfintechlab/FOMC-RoBERTa |
0.8 |
0.0 |
text-classification |
| 208 |
OpenMOSS-Team/MOSS-VL-Realtime-NF4 |
0.7 |
1.8 |
video-text-to-text |
| 209 |
iNLP-Lab/Myna-Hokkien |
0.4 |
0.5 |
audio-to-audio |