| 1 | tiny-mistralopenaccess-ai-collective | Text Generation | 15 | — | 15 | — |
| 2 | Qwen3.8-27B-Uncensored-FP8-Q4_K_M-GGUFtheresa00l | Image Text to Text | 15 | — | 15 | — |
| 3 | langcache-embed-v1redis | Sentence Similarity | 15 | — | 15 | 149M |
| 4 | MOSS-VL-Instruct-0708-NF4OpenMOSS-Team | Video Text To Text | 15 | — | 15 | 11.3B |
| 5 | BananaMind-2-MicroBananaMind | Text Generation | 15 | — | 15 | 3.2M |
| 6 | RaDialog-interactive-radiology-report-generationChantalPellegrini | Image Text to Text | 15 | — | 15 | — |
| 7 | LFM2.5-VL-3B-MLX-bf16LiquidAI | Image Text to Text | 15 | — | 15 | 3.1B |
| 8 | LFM2.5-VL-3B-MLX-8bitLiquidAI | Image Text to Text | 15 | — | 15 | 1.2B |
| 9 | siglip-large-patch16-256google | Zero-Shot Image Classification | 15 | — | 15 | 652M |
| 10 | cleardesert-ant-labs | Audio to Audio | 15 | — | 15 | — |
| 11 | EVA-Qwen2.5-32B-v0.2-GGUFbartowski | Text Generation | 15 | — | 15 | — |
| 12 | Unichat-llama3-Chinese-8B-28KUnicomLLM | Text Generation | 15 | — | 15 | — |
| 13 | msmarco-MiniLM-L6-v3sentence-transformers | Sentence Similarity | 15 | — | 15 | 22.7M |
| 14 | DeepSeek-V4-Pro-Qwen3.5-4BJackrong | Text Generation | 15 | — | 15 | 4.7B |
| 15 | Qwen2.5-Math-7B-Instruct-GGUFbartowski | Text Generation | 15 | — | 15 | — |
| 16 | siglip2-base-patch16-384google | Zero-Shot Image Classification | 15 | — | 15 | 375M |
| 17 | MiniMax-H3-FL2VA-MLX-Serve-8bitddalcu | Text to Video | 15 | — | 15 | — |
| 18 | GRM-3.2-Sky-ONYX-GGUFel4 | Text Generation | 15 | — | 15 | — |
| 19 | mistral-community_pixtral-12b-GGUFbartowski | Image Text to Text | 15 | — | 15 | — |
| 20 | Qwen3.6-27B-Fable-Fusion-711-MTPLX-8bitphilipjohnbasile | Image Text to Text | 15 | — | 15 | 26.9B |
| 21 | mms-tts-frafacebook | Text to Speech | 15 | — | 15 | 36.3M |
| 22 | ThinkingCap-Qwen3.6-27B-NVFP4bottlecapai | Image Text to Text | 15 | — | 15 | 16.7B |
| 23 | MiLMMT-46-12B-v1.0xiaomi-research | Translation | 15 | — | 15 | 12.2B |
| 24 | Step-3.5-Flash-GGUFggml-org | — | 15 | — | 15 | — |
| 25 | nli-roberta-basecross-encoder | Zero-Shot Classification | 15 | — | 15 | 125M |
| 26 | Qwen2.5-VL-72B-Instruct-FP8-dynamicRedHatAI | Image Text to Text | 15 | — | 15 | 73.4B |
| 27 | hubert-large-speech-emotion-recognition-russian-dusha-finetunedxbgoose | Audio Classification | 15 | — | 15 | 316M |
| 28 | opus-mt-tc-big-en-esHelsinki-NLP | Translation | 15 | — | 15 | 233M |
| 29 | InternScience_Agents-A1-4B-GGUFbartowski | Image Text to Text | 15 | — | 15 | — |
| 30 | rubert-base-cased-sentiment-rusentimentblanchefort | Text Classification | 15 | — | 15 | 178M |
| 31 | Llama-3.1-405B-Instruct-NVFP4nvidia | — | 15 | — | 15 | 230B |
| 32 | Soofi-S-Isar-PreviewSoofi-Project | Text Generation | 15 | — | 15 | 31.6B |
| 33 | gemma-4-12B-it-qat-OptiQ-4bitmlx-community | Text Generation | 15 | — | 15 | 11.9B |
| 34 | Agents-A1-Uncensored-MTP-APEX-GGUFSC117 | Text Generation | 15 | — | 15 | — |
| 35 | Mistral-Nemo-Instruct-2407-4bitmlx-community | — | 15 | — | 15 | 1.9B |
| 36 | Kimi-K3-GGUFAtomicChat | Image Text to Text | 15 | — | 15 | — |
| 37 | GigaChat3.1-10B-A1.8B-bf16ai-sage | Text Generation | 15 | — | 15 | 11.5B |
| 38 | Qwen3.6-27B-F451-AND-TRI-Polar-Ultra-Pro-Writer-Uncensored-HereticDavidAU | Image Text to Text | 15 | — | 15 | 27.4B |
| 39 | CLIP-ViT-B-32-xlm-roberta-base-laion5B-s13B-b90klaion | — | 15 | — | 15 | — |
| 40 | texifyvikp | Image Text to Text | 15 | — | 15 | 312M |
| 41 | vit_base_patch14_reg4_dinov2.lvd142mtimm | Image Feature Extraction | 15 | — | 15 | 86.6M |
| 42 | rev-animatedstablediffusionapi | Text to Image | 15 | — | 15 | 860M |
| 43 | mediapipeComfy-Org | — | 15 | — | 15 | — |
| 44 | bekko-embedding-v1-a8mhotchpotch | Sentence Similarity | 15 | — | 15 | 106M |
| 45 | gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-i1-GGUFmradermacher | — | 15 | — | 15 | — |
| 46 | granite-swash-3b-a600mibm-granite | Text Generation | 15 | — | 15 | 3B |
| 47 | parakeet-rnnt-0.6bnvidia | Speech Recognition | 15 | — | 15 | 617M |
| 48 | Ornith-9B-GGUFAtomicChat | Text Generation | 15 | — | 15 | — |
| 49 | LTX_2.3_Cinematic_Sci-fi-Cyberpunk_Style_LoRavrgamedevgirl84 | Text to Video | 15 | — | 15 | — |
| 50 | Qwen3-VL-30B-A3B-Thinking-AWQQuantTrio | Text Generation | 15 | — | 15 | 31.1B |