| 1 | droplychee-1.0-27bdroplychee | Image Text to Text | 74 | 0% | 4 | 27.8B | Jul 17, 2026 |
| 2 | OneJev-0.8B-ONNXonnx-community | Image Text to Text | 74 | — | 1 | — | Sep 30, 2026 |
| 3 | Laguna-S-2.1-JANG_6M-CRACKdealignai | Text Generation | 73 | — | 0 | 118B | Jul 26, 2026 |
| 4 | Qwen3-ASR-1.7Blitert-community | Speech Recognition | 71 | — | 1 | — | Oct 3, 2026 |
| 5 | gpt-oss-120b-Uncensored-GGUFmradermacher | Text Generation | 71 | — | 0 | — | Sep 28, 2026 |
| 6 | VGGT-Omega-1B-512-bf16mlx-community | Image To 3d | 70 | — | 1 | 1.1B | Sep 28, 2026 |
| 7 | interfaze-1-liteinterfaze-ai | Image Text To Image | 69 | — | 52 | — | Oct 3, 2026 |
| 8 | Qwen3-VL-4B-Instruct-heretic-Semantic-Same-GGUFmradermacher | — | 69 | — | 0 | — | Sep 23, 2026 |
| 9 | Mistral-Small-4-119B-2603.dflashRedHatAI | — | 69 | — | 2 | 2.2B | Jul 23, 2026 |
| 10 | map-anything-apache-fp16mlx-community | Image To 3d | 69 | — | 1 | 1.2B | Sep 29, 2026 |
| 11 | North-Micro-Vision-Instruct-5bit-mlxOpenMed | Image Text to Text | 69 | — | 1 | 2.5B | Aug 12, 2026 |
| 12 | Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-oQ2e-mtpmlx-community | — | 69 | — | 0 | 27.8B | Sep 17, 2026 |
| 13 | phartakos-mlxmlx-community | Audio to Audio | 68 | — | 1 | 24M | Oct 1, 2026 |
| 14 | GLM5.3-Flash-E224-DGX-Sparkautotrust | Image Text to Text | 68 | — | 74 | 128B | Oct 6, 2026 |
| 15 | qwen3-4b-structured-output-merged-stage-a-OBLITERATEDOBLITERATUS | — | 68 | — | 2 | 4B | Aug 7, 2026 |
| 16 | EmbeddingGemma-300M-Tensor-G4-NPUlitert-community | Embeddings | 68 | — | 1 | — | Sep 19, 2026 |
| 17 | Jamba2-3B-Turkish-SFT-v1-GGUFmradermacher | — | 67 | — | 0 | — | Aug 24, 2026 |
| 18 | grok_demon_7b_v2.6-GGUFmradermacher | — | 67 | — | 0 | — | Sep 23, 2026 |
| 19 | Apertus-v1.5-70B-baseswiss-ai | Image Text to Text | 67 | — | 3 | 71.9B | Sep 23, 2026 |
| 20 | AREX-2-FP8prithivMLmods | Image Text to Text | 67 | — | 3 | 27.4B | Oct 1, 2026 |
| 21 | Qwen3.8-27B-speculator.dspark-previewRedHatAI | — | 66 | — | 2 | 2B | Sep 16, 2026 |
| 22 | single-floppy-346k-merged-ONNXonnx-community | Text Generation | 66 | — | 1 | — | Aug 7, 2026 |
| 23 | arcane-7b-GGUFmradermacher | — | 66 | — | 0 | — | Sep 2, 2026 |
| 24 | GaussianMindBAAI | Audio Text To Text | 66 | — | 1 | 5.6B | Sep 3, 2026 |
| 25 | MiniCPM5-2B-MXFP8sahilchachra | Text Generation | 65 | — | 0 | 2.5B | Sep 11, 2026 |
| 26 | ImageShield-MMCF-2B-vlprithivMLmods | Image Text to Text | 65 | — | 2 | 2.1B | Aug 28, 2026 |
| 27 | harmony-v2-GGUFmradermacher | — | 65 | — | 0 | — | Jul 28, 2026 |
| 28 | ChindaMT-4B-GGUFmradermacher | Translation | 64 | — | 0 | — | Sep 24, 2026 |
| 29 | fine_tuned_model_v3hermoine1234 | Sentence Similarity | 63 | ▲0.0%(up) | 0 | 278M | Jul 28, 2026 |
| 30 | TextSynth-4B-0926-GGUFmradermacher | — | 63 | — | 0 | — | Sep 24, 2026 |
| 31 | Llama-3.1-8B-Turkish-GGUFmradermacher | — | 62 | — | 0 | — | Sep 24, 2026 |
| 32 | Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-oQ2-mtpmlx-community | — | 62 | — | 0 | 27.8B | Sep 17, 2026 |
| 33 | MagenticBrain-8bitmlx-community | Text Generation | 62 | — | 2 | 14.8B | Jul 29, 2026 |
| 34 | Vinci-Cyber-8B-1.0-GGUFmradermacher | — | 61 | — | 0 | — | Sep 23, 2026 |
| 35 | MemGUI-8B-RL-GGUFmradermacher | Reinforcement Learning | 61 | — | 0 | — | Sep 18, 2026 |
| 36 | tiny-random-qwen3-forced-aligneroptimum-intel-internal-testing | — | 61 | — | 1 | 10.3M | Sep 15, 2026 |
| 37 | SenseNova-U1.5-8B-MoT-bf16mlx-community | Any to Any | 60 | — | 0 | 17.5B | Aug 24, 2026 |
| 38 | Keural-Cortex-8B-v1.0-GGUFmradermacher | Text Generation | 60 | — | 0 | — | Sep 23, 2026 |
| 39 | K2-Horizon-7B-MLX-8bitabenzerps | Text Generation | 60 | — | 0 | 9B | Sep 3, 2026 |
| 40 | llm-jp-4-vl-9b-mlx-4bitmlx-community | Image Text to Text | 59 | — | 0 | 9B | Sep 7, 2026 |
| 41 | llmjp-4-vl-9b-mlx-4bitmlx-community | Image Text to Text | 59 | — | 0 | 9B | Sep 7, 2026 |
| 42 | Lumo-1-1.5B-Chat-GGUFmradermacher | — | 58 | — | 0 | — | Sep 23, 2026 |
| 43 | qwen3_vit_306m_enc.qwen_drive_1_0_4btimm | Image Feature Extraction | 58 | — | 0 | 333M | Sep 17, 2026 |
| 44 | orato-asr-hindi-v1tryorato | Speech Recognition | 58 | ▲0.7%(up) | 30 | 782M | Jul 29, 2026 |
| 45 | Laguna-XS-2.1-JANG_2L-CRACKdealignai | Text Generation | 58 | — | 0 | 33.4B | Jul 25, 2026 |
| 46 | Xiaomi-Robotics-U0XiaomiRobotics | Any to Any | 58 | — | 31 | 34.1B | Jul 13, 2026 |
| 47 | ViCLIP-L-14-BVD-V-50M-s50M-b32Klaion | Video Classification | 58 | — | 1 | 428M | Aug 25, 2026 |
| 48 | hua-1.7b-GGUFmradermacher | Reinforcement Learning | 58 | — | 0 | — | Sep 24, 2026 |
| 49 | Swift-Qwen3.8-Flash-Nextukisai | Image Text to Text | 57 | — | 16 | 180B | Sep 22, 2026 |
| 50 | RE-USE-GGUFaudio-cpp | Audio to Audio | 56 | — | 0 | — | Oct 1, 2026 |