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.
LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervisedtiny-random-Llama-3-loracolqwen2.5-3b-multilingual-v1.0uno-qwen3-8Bopt-350m-loraminimax_h3_fl2v_lightx2v_4step_int8-convrot_comfyqwen3-moe-pre-v5-loraThinkSafe-Qwen3-0.6Bqwen3_06B_lora_mathMistral-Medium-3.5-128B-Eschaton-Uncensored-GGUFLlama-3.2-3B-TechWriter-Instruct-UnslothB3_Qwen2_2Bgemma-4-31b-it-sft-lora-resumed-lastgemma-4-31b-it-lora-lastgemma-4-31b-honesty-sft-dishonest-advsys-ep5Llama-3.1-8B-MultiReflection-Instruct-i1-GGUFQwen3.8-27B-nz-wvs-full_string_distribution-overallmetallama3.2-3b-learnedColQwen2.5-3b-multilingual-v1.0ner-pt-f1-v1-qwen35-0-8b-specific-paramopama-seed42editlens_Llama-3.2-3BLlama-3.2-3B-TechWriter-Instruct-Unsloth-i1-GGUFLlama-3.1-8B-MultiReflection-Instruct-GGUFMiniMax-H3-Turbo-Lora-Diffuserswhisper-large-v3-turbo-darijaQwen3-4B-Base-HIP-adapterQwen3-0.6B-TLDR-LoraQwen3.8-27B-Yes-Man-uncensored-i1-GGUFGhostWriterLlama-3.2-1B-DPO-i1-GGUFUIGEN-T3-14B-Preview-i1-GGUF