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-instructQwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTPgranite-embedding-107m-multilingual-GGUFnvidia_Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual-GGUFQwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP-XSCustomerLMLlama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32B-GGUFMultilingual-Expressive-TTS-1.7Bgranite-embedding-278m-multilingual-GGUFLlama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-COGITO-Deep-Reasoning-32B-GGUFQwen2-7B-Multilingual-RP-GGUFClickBook-Gemma-4-E2B-multi-IQ4_XSpaza-Phi-4-multimodal-instructcomp-vs-like-1B-unigramlm-multi-128kcomp-vs-like-1B-bpe-multi-128kcomp-vs-like-1B-topdowncomp-multi-128kcomp-vs-like-1B-bottomupll-exact-multi-128kPhi-4-multimodal-instructgranite-embedding-278m-multilingual-GGUFMultilingual-TTS-1.7B-BaseURCHIN_BabyLM2026_Multilingualfunctiongemma-finetuned-g1-multilingualPhi-4-multimodal-instruct-abliteratedgranite-embedding-107m-multilingual-GGUFgoogle-bert-bert-base-multilingual-casedMultilingual-Expressive-TTS-0.6BLlama-3.3-Nemotron-70B-Reward-MultilingualLlama-3_3-Nemotron-Super-49B-GenRM-MultilingualLlama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32Bbabylm-2026-multilingual-uniform-100M-v2