models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Phi-4-multimodal-instructbabylm-multimodal-baseline-flamingotiny-random-phi-4-multimodalMistral-MOE-4X7B-Dark-MultiVerse-Uncensored-Enhanced32-24B-ggufsuzume-llama-3-8B-multilingualsuzume-llama-3-8B-multilingual-orpo-borda-top25orpheus-3b-tts-multilingualMultiVerse_70Bmultimaster-7b-v6multi_verse_modelsuzume-llama-3-8B-multilingual-orpo-borda-fullsuzume-llama-3-8B-multilingual-orpo-borda-top75suzume-llama-3-8B-multilingual-orpo-borda-halfQwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTPparler-tts-mini-multilingual-v1.1granite-embedding-107m-multilingual-GGUFHypernova-60B-2602Hypernova-60B-2605multiagent-orchestratorcodegen-350M-multiCustomerLMnvidia_Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual-GGUFMulti_verse_modelInex12-7B-GGUFMulti_verse_modelExperiment26-7B-GGUFQwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP-XSLlama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32B-GGUFctxl-rerank-v2-instruct-multilingual-1b-fp8Multilingual-Expressive-TTS-1.7BQwen3.5-4B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0-i1-GGUFgranite-embedding-278m-multilingual-GGUF