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.
xlm-roberta-base-lora-language-detectiongpt-oss-sanguine-20b-v1-i1-GGUFWordStitch-4Bgpt-oss-sanguine-20b-v1-GGUFMiniMax-H3-Prompt-Rewriter-LoRA-Omniqwen3vl-8b-claw-stage3-v2-loraveriloop-coder-e1mmbert-intent-classifier-loraQwen2.5-7B-Instruct-CharacterEnhanceclaude-sonnet5-qwen-thinkingclaude-llama-8B-think-GGufTARS-Llama-3-8B-Instruct-GGUFresidual_fusionLFM2.5-350M-Extract-ML-LoRAsuper-like-claude-gguf-v2turkish_focused-multilingual-e5-smallAniCoord-Qwen3-8B-QLoRA-v1Qwen3-8B-LegalCitation-GRPO-600LinguaForge-Qwen3.5-0.8B-zhTW-en-japrivacy-gateway-v4-qwen2.5-0.5bGGUF.granite-4.0-Improved-Enhanced-Refinedgemma-4-E2B-duplexclaude-sonnet5-qwen-thinkingzh-ppt-voice-agent-model-lora-support-interruptming-vintage-qwen3b-loraqwen3-6-27b-chinese-xianxia-lora-v2DATA-AI_Chat_2_0.5B-Intruct-GGUFqwen3-6-27b-chinese-crime-fiction-lora-v2unmuzzle-qwen14b-honesty-loratalyno-whisper-small-finance