| 1 | gemma-3-27b-it-GGUFMaziyarPanahi | Text Generation | 8 | — | 8 | — |
| 2 | Qwen3-Coder-480B-A35B-Instruct-AWQQuantTrio | Text Generation | 8 | — | 8 | 480B |
| 3 | opus-mt-tc-big-en-frHelsinki-NLP | Translation | 8 | — | 8 | 231M |
| 4 | infoxlm-basemicrosoft | Fill Mask | 8 | — | 8 | — |
| 5 | Qwen3.6-27B-W4A16-G128LibertAIDAI | Image Text to Text | 8 | — | 8 | 27.8B |
| 6 | Qwen2.5-0.5B-Instruct-4bitmlx-community | Text Generation | 8 | — | 8 | 77.3M |
| 7 | tiny-mbartsshleifer | — | 8 | — | 8 | — |
| 8 | Gemma-4-12B-NVFP4AxionML | Image Text to Text | 8 | — | 8 | 7.7B |
| 9 | gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic-i1-GGUFmradermacher | — | 8 | — | 8 | — |
| 10 | InternVL3_5-8B-HFOpenGVLab | Image Text to Text | 8 | — | 8 | 8.5B |
| 11 | Vikhr-Nemo-12B-Instruct-R-21-09-24-Q4_K_M-GGUFVlSav | — | 8 | — | 8 | — |
| 12 | GLM-4.5-Airunsloth | Text Generation | 8 | — | 8 | 110B |
| 13 | wav2vec2-quran-phoneticsTBOGamer22 | Speech Recognition | 8 | — | 8 | 94.4M |
| 14 | mbarthezmoussaKam | Fill Mask | 8 | — | 8 | — |
| 15 | swiftformer-xsMBZUAI | Image Classification | 8 | — | 8 | 3.5M |
| 16 | Qwen3-Omni-30B-A3B-Instruct-AWQ-8bitcyankiwi | Any to Any | 8 | — | 8 | 13.8B |
| 17 | Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-heretic-GGUFgorbatjovy | — | 8 | — | 8 | — |
| 18 | llm-jp-3-150mllm-jp | Text Generation | 8 | — | 8 | 152M |
| 19 | Huihui-Qwen3.5-0.8B-abliterated-GGUFmradermacher | — | 8 | — | 8 | — |
| 20 | Qwen3.5-35B-A3B-MTP-ONLY-GGUFa4lg | — | 8 | — | 8 | — |
| 21 | Muse-Glimmer-30B-GGUFAtomicChat | Image Text to Text | 8 | — | 8 | — |
| 22 | trellis-image-largejetx | Image To 3d | 8 | — | 8 | — |
| 23 | LanguageBind_Video_FTLanguageBind | Zero-Shot Image Classification | 8 | — | 8 | — |
| 24 | DeepSeek-V4-Flash-0731-GGUFbullerwins | Text Generation | 8 | — | 8 | — |
| 25 | ThinkingCap-Qwen3.6-27B-NVFP4morosystems | Image Text to Text | 8 | — | 8 | 15.2B |
| 26 | Qwen3.6-27B-NVFP4mmangkad | Text Generation | 8 | — | 8 | 20.3B |
| 27 | Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive-GenRMHauhauCS | — | 8 | — | 8 | — |
| 28 | llava-next-72b-hfllava-hf | Image Text to Text | 8 | — | 8 | 72.7B |
| 29 | Qwen3.8-9B-heretic-uncensored-i1-GGUFmradermacher | — | 8 | — | 8 | — |
| 30 | Mistral-Small-24B-Instruct-2501unsloth | Text Generation | 8 | — | 8 | 23.6B |
| 31 | Mursit-Large-TR-Retrievalnewmindai | Sentence Similarity | 8 | — | 8 | 404M |
| 32 | ttm-r3ibm-research | Time Series Forecasting | 8 | — | 8 | 1.4M |
| 33 | Qwen3.8-27B-DFlash2-W4A16syvai | — | 8 | — | 8 | 1.9B |
| 34 | Luminex-34B-v0.1ConvexAI | Text Generation | 8 | — | 8 | 34.4B |
| 35 | S-PubMedBert-MedQuADTimKond | Sentence Similarity | 8 | — | 8 | 109M |
| 36 | whisper-large-v3-turbo-latammarianbasti | Speech Recognition | 8 | — | 8 | 809M |
| 37 | gemma-4-E2B-it-qat-w4a16-ctgoogle | Any to Any | 8 | — | 8 | 5.6B |
| 38 | Qwen3.5-9B-Q4_K_M-GGUFjc-builds | Text Generation | 8 | — | 8 | — |
| 39 | plt5-baseallegro | Translation | 8 | — | 8 | — |
| 40 | robbert-2023-dutch-baseDTAI-KULeuven | Fill Mask | 8 | — | 8 | 124M |
| 41 | Rosetta-inferencetencent | — | 8 | — | 8 | — |
| 42 | mathstral-7B-v0.1-GGUFMaziyarPanahi | Text Generation | 8 | — | 8 | — |
| 43 | English_Grammar_Checkerabdulmatinomotoso | Text Classification | 8 | — | 8 | — |
| 44 | Mistral-Small-3.2-24B-Instruct-2506-GGUFlmstudio-community | Image Text to Text | 8 | — | 8 | — |
| 45 | Qwen3.8-27B-Uncensored-OrcaRouter-MLX-4bitchimingw | Image Text to Text | 8 | — | 8 | 5.8B |
| 46 | bge-small-en-v1.5-ggufCompendiumLabs | — | 8 | — | 8 | — |
| 47 | LFM2.5-1.2B-Instructunsloth | Text Generation | 8 | — | 8 | 1.2B |
| 48 | Qwen3-VL-2B-Instruct-unsloth-bnb-4bitunsloth | Image Text to Text | 8 | — | 8 | 2.2B |
| 49 | ARBERTv2UBC-NLP | Fill Mask | 8 | — | 8 | 164M |
| 50 | Qwen3-14B-MLX-4bitlmstudio-community | Text Generation | 8 | — | 8 | 2.3B |