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.
JoyAI-LLM-Flash-MXFP8-last-6-BF16dots.llm1.basemmbert32k-feedback-detector-mergedVela-1.0-Encoder-307M-Embeddingmmbert32k-modality-router-mergedMistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic-GGUFQZhou-Embeddingmmbert-32k-yarnVela-1.0-Encoder-307M-PIIVela-1.0-Encoder-307M-Feedbackdots.llm1.inst-GGUFQwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-uncensored-heretic-GGUFVela-1.0-Encoder-307MShizhenGPT-7B-LLM-i1-GGUFrednote-hilab_dots.llm1.inst-GGUFZYH-LLM-Qwen2.5-14B-V3-i1-GGUFyihao-llm-7b-i1-GGUFVela-1.0-Encoder-307M-RerankerZYH-LLM-Qwen2.5-14B-V2-i1-GGUFYoutu-LLM-2B-GGUFVela-1.0-Encoder-307M-ModalityGLM-4-32B-0414-uncensored-heretic-v2-GGUFPathumma-llm-text-1.0.0NOESIS-Qwen3-TTS-1.7B-Talker-Combo-LLM2-ASR2-BF16dots.llm1.instPathumma-llm-text-1.0.0-i1-GGUFZYH-LLM-Qwen2.5-14B-i1-GGUFTaiwan-LLM-7B-v2.0-base-i1-GGUFNOESIS-Qwen3-TTS-1.7B-Talker-Combo-LLM2-ASR2-BF16-GGUFZYH-LLM-Qwen2.5-14B-V4-i1-GGUF