| 1 | ECG-R1-8B-RLPKUDigitalHealth | Image Text to Text | 3 | — | 3 | 8.9B |
| 2 | kokoro-ruzaakirio | Text to Speech | 3 | — | 3 | — |
| 3 | pony-diffusion-v6-xl-GGUFoffgrid-ai | Text to Image | 3 | — | 3 | — |
| 4 | convnext_small.fb_in22k_ft_in1ktimm | Image Classification | 3 | — | 3 | 50.2M |
| 5 | wav2vec2-xls-r-1b-germanjonatasgrosman | Speech Recognition | 3 | — | 3 | — |
| 6 | Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER-i1-GGUFmradermacher | — | 3 | — | 3 | — |
| 7 | Qwen3-14B-MLX-8bitlmstudio-community | Text Generation | 3 | — | 3 | 4.2B |
| 8 | Mistral-7B-Instruct-v0.3mistral-community | Text Generation | 3 | — | 3 | 7.2B |
| 9 | gemma-3-4b-it-heretic-v1.2-i1-GGUFmradermacher | — | 3 | — | 3 | — |
| 10 | bge-m3-ONNXonnx-community | Sentence Similarity | 3 | — | 3 | — |
| 11 | Voxtral-Mini-4B-Realtime-2602-fp16mlx-community | Speech Recognition | 3 | — | 3 | 4.4B |
| 12 | flux2_klein_9B_Realism_Engine_V2Keltezaa | Text to Image | 3 | — | 3 | — |
| 13 | mdeberta-v3-base-prompt-injectionproventra | Text Classification | 3 | — | 3 | 279M |
| 14 | Qwen3.6-35B-A3B-NVFP4-Fast-GGUFFreedomAISVR | Image Text to Text | 3 | — | 3 | — |
| 15 | jina-embeddings-v5-omni-nano-text-matchingjinaai | Embeddings | 3 | — | 3 | 948M |
| 16 | pi0fast-liberolerobot | — | 3 | — | 3 | 3.4B |
| 17 | LFM2.5-VL-3B-Uncensored-GGUFSC117 | Image Text to Text | 3 | — | 3 | — |
| 18 | Agents-A1-NVFP4r0b0tlab | Text Generation | 3 | — | 3 | 18.9B |
| 19 | NVIDIA-Nemotron-Labs-3-Elastic-12B-A2B-i1-GGUFmradermacher | — | 3 | — | 3 | — |
| 20 | sd15.juggernaut.reborn.unetrefiners | Image To Image | 3 | — | 3 | 860M |
| 21 | Qwen3-Embedding-4B-mxfp8mlx-community | Embeddings | 3 | — | 3 | 1.1B |
| 22 | baidu_ERNIE-4.5-21B-A3B-Thinking-GGUFbartowski | Text Generation | 3 | — | 3 | — |
| 23 | whisper-large-v3-turbo-fp16mlx-community | Speech Recognition | 3 | — | 3 | 807M |
| 24 | granite-3.2-8b-instruct-GGUFlmstudio-community | Text Generation | 3 | — | 3 | — |
| 25 | EVA-Qwen2.5-14B-v0.0-GGUFbartowski | Text Generation | 3 | — | 3 | — |
| 26 | Heimdallr-27B-v0.35-GGUFReadyArt | — | 3 | — | 3 | — |
| 27 | Qwen1.5-4B-Chat-AWQQwen | Text Generation | 3 | — | 3 | 4B |
| 28 | KAT-Coder-V2.5-Dev-VL-Flashbeyoru | Image Text to Text | 3 | — | 3 | 18.9B |
| 29 | focalcodec_12_5hzlucadellalib | Audio to Audio | 3 | — | 3 | 145M |
| 30 | stella-pl-retrieval-mini-8ksdadas | Sentence Similarity | 3 | — | 3 | 434M |
| 31 | bridgetower-base-itm-mlmBridgeTower | — | 3 | — | 3 | — |
| 32 | Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUFmradermacher | — | 3 | — | 3 | — |
| 33 | Qwen3-VL-32B-Instruct-ultra-uncensored-heretic-GGUFllmfan46 | Image Text to Text | 3 | — | 3 | — |
| 34 | Qwen3.5-27B-quantized.w4a16apolo13x | Image Text to Text | 3 | — | 3 | 27.5B |
| 35 | Llama-3-Swallow-8B-Instruct-v0.1-ggufmmnga | — | 3 | — | 3 | — |
| 36 | gemma-4-26B-A4B-it-oQ4e-mtpJundot | — | 3 | — | 3 | 5B |
| 37 | ModelScopeckpt | — | 3 | — | 3 | — |
| 38 | vibevoice-asr-bitnet-GGUFcstr | Speech Recognition | 3 | — | 3 | — |
| 39 | xlm-roberta-large-english-cap-v5poltextlab | Text Classification | 3 | — | 3 | 560M |
| 40 | whisper-large-v3-turbo-bulgarian-bulgariasam8000 | Speech Recognition | 3 | — | 3 | 809M |
| 41 | MiniLM-L3-H384-uncasednreimers | Embeddings | 3 | — | 3 | — |
| 42 | Qwen3.5-122B-A10B-abliterated-NVFP4bjk110 | Text Generation | 3 | — | 3 | 71.2B |
| 43 | dots.ocr-i1-GGUFmradermacher | Image to Text | 3 | — | 3 | — |
| 44 | Llama-3.1-8B-Instruct-4bitmlx-community | Text Generation | 3 | — | 3 | 1.3B |
| 45 | bert-base-multilingual-uncased-sentimentXenova | Text Classification | 3 | — | 3 | — |
| 46 | Qwen3-14B-f16geoffmunn | Text Generation | 3 | — | 3 | — |
| 47 | gpt-oss-20b-Derestricted-GGUFMaziyarPanahi | Text Generation | 3 | — | 3 | — |
| 48 | Huihui-Kimi-Linear-48B-A3B-Instruct-abliterated-i1-GGUFmradermacher | — | 3 | — | 3 | — |
| 49 | demodokos-foundry-tts-v4cmp-nct | Text to Speech | 3 | — | 3 | — |
| 50 | vitpose-plus-largeusyd-community | Keypoint Detection | 3 | — | 3 | 434M |