| 1 | whisper-base.en-fp16mlx-community | Speech Recognition | 78 | — | 0 | 71.8M |
| 2 | Parable-SmolLM3-3B-Claude-Fable-5AnkitAI | Text Generation | 78 | — | 3 | 3.1B |
| 3 | wavlm-large-english-phoneme-ONNXonnx-community | Speech Recognition | 78 | — | 0 | — |
| 4 | openmusicjadechoghari | Text to Audio | 78 | ▲1.3%(up) | 73 | — |
| 5 | ruviewruv | Other | 78 | ▲1.6%(up) | 35 | — |
| 6 | SambaLingo-Hungarian-Chatsambanovasystems | Text Generation | 78 | ▲0.1%(up) | 48 | 6.9B |
| 7 | simlm-base-msmarco-finetunedintfloat | Embeddings | 77 | ▲0.1%(up) | 2 | — |
| 8 | Omni-Edu-4B-GGUFmradermacher | — | 77 | — | 0 | — |
| 9 | fine_tuned_model_v3hermoine1234 | Sentence Similarity | 77 | ▲0.0%(up) | 0 | 278M |
| 10 | mistral7b_ocr_to_json_v1mychen76 | Text Generation | 77 | ▲0.1%(up) | 99 | 7.2B |
| 11 | gemma-4-E2B-it-abliteratedwangzhang | — | 77 | 0% | 7 | 5.1B |
| 12 | angle-bert-base-uncased-nli-en-v1SeanLee97 | Embeddings | 77 | 0% | 5 | — |
| 13 | Hy-MT1.5-1.8B-1.25bittencent | Translation | 77 | — | 32 | 2B |
| 14 | Muse-Glimmer-30B-JANG_2D-CRACKdealignai | Image Text to Text | 77 | — | 0 | 29.8B |
| 15 | Lens-3.8B-bf16mlx-community | Text to Image | 77 | — | 4 | 4.1B |
| 16 | SambaLingo-Arabic-Chatsambanovasystems | Text Generation | 77 | ▲0.0%(up) | 64 | 6.9B |
| 17 | whisper-base-4bitmlx-community | Speech Recognition | 77 | — | 0 | 71.8M |
| 18 | UI-DETR-1racineai | Object Detection | 77 | — | 48 | — |
| 19 | colbert-muvera-smallNeuML | Sentence Similarity | 77 | — | 12 | 33.4M |
| 20 | kobertXenova | Embeddings | 77 | ▲1.2%(up) | 0 | — |
| 21 | MythoMax-L2-13B-GGMLTheBloke | — | 77 | ▲0.7%(up) | 84 | — |
| 22 | Magic-Wan-Image-v1.0wikeeyang | Text to Image | 77 | ▲0.3%(up) | 35 | — |
| 23 | qwen3-4b-structured-output-merged-stage-a-OBLITERATEDOBLITERATUS | — | 77 | — | 2 | 4B |
| 24 | wd-v1-4-vit-tagger-v2SmilingWolf | — | 77 | ▲0.3%(up) | 69 | — |
| 25 | HuMobytedance-research | Image To Video | 77 | ▲1.0%(up) | 268 | — |
| 26 | gemma-3-1b-pt-qat-q4_0-ggufgoogle | Text Generation | 77 | ▲0.6%(up) | 17 | — |
| 27 | OpenAssistant-Llama2-13B-Orca-8K-3319-GGMLTheBloke | Text Generation | 77 | — | 53 | — |
| 28 | Mann-E_Dreamsmann-e | Text to Image | 77 | ▲0.0%(up) | 74 | 2.6B |
| 29 | gemma-3n-E4B-it-text-4bit-dwqmlx-community | Text Generation | 77 | — | 0 | 6.9B |
| 30 | opus-v1.2-llama-3-8bdreamgen | Text Generation | 77 | ▲0.2%(up) | 53 | 8B |
| 31 | audiogen-medium-mlxmlx-community | Text to Audio | 77 | — | 2 | 1.9B |
| 32 | Italy-10B-GGUFmradermacher | — | 77 | — | 3 | — |
| 33 | RTMPose-Face-WFLW-LiteRTlitert-community | Keypoint Detection | 77 | — | 0 | — |
| 34 | WizardLM-13B-V1.2-GGMLTheBloke | — | 77 | — | 55 | — |
| 35 | wizard-vicuna-13B-HFTheBloke | Text Generation | 77 | ▲0.0%(up) | 49 | — |
| 36 | internlm-xcomposer2d5-ol-7binternlm | Visual Question Answering | 76 | ▲1.4%(up) | 50 | — |
| 37 | bert-base-multilingual-cased-finetuned-conll02-spanishdbmdz | Token Classification | 76 | ▲0.3%(up) | 1 | 178M |
| 38 | TurboSparse-MixtralTiiny | Embeddings | 76 | — | 46 | 51.8B |
| 39 | mandarin-wav2vec2-aishell1kehanlu | Speech Recognition | 76 | ▲0.0%(up) | 2 | — |
| 40 | hubert-base-english-ipa-ONNXonnx-community | Speech Recognition | 76 | — | 0 | — |
| 41 | mini-magnum-12b-v1.1intervitens | Text Generation | 76 | ▲0.1%(up) | 80 | 12.2B |
| 42 | ESMC-300M-sae-layer23-k64-codebook16384biohub | Embeddings | 76 | — | 0 | — |
| 43 | OTel-LLM-0.6B-ITfarbodtavakkoli | Text Generation | 76 | — | 0 | — |
| 44 | Yi-34B-200K-RPMergebrucethemoose | Text Generation | 76 | ▲0.3%(up) | 60 | 34.4B |
| 45 | whisper-small-ita-ONNXonnx-community | Speech Recognition | 76 | — | 0 | — |
| 46 | viet-ttsdangvansam | Text to Speech | 76 | — | 27 | — |
| 47 | whisper-large-v3-turbodeepdml | Speech Recognition | 76 | ▲0.0%(up) | 17 | 809M |
| 48 | Baka-DiffusionHosioka | Text to Image | 76 | ▲0.1%(up) | 95 | — |
| 49 | Spaetzle-v85-7b-GGUFmradermacher | — | 76 | — | 1 | — |
| 50 | Agnes-3.0-Flash-oQ4emlx-community | — | 76 | — | 0 | — |