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.
STEVE-R1-7B-SFT-i1-GGUFSTEVE-R1-7B-SFT-GGUFqwen2.5-1.5b-wordle-grpo-mergedqwen2.5-3b-grpo-gsm8kQwen3.5-9B-GGUF-Quant-Labchaty-qwen3.5-4b-design-GGUFllama-3.1-8b-taiwan-chat-ggufLTX-2.3alphaduel-qwen3-0.6b-sft_v0FineTune_LLama3.1_4Bit_Use_jojo0217_korean_safe_conversation_and_unsloth_with_RTX3090CoVT-Phase2-3expert-StrictFineTune_LLama3.1_Use_jojo0217_korean_safe_conversation_and_unsloth_f16qwen3-embedding-0.6b-lrat-full80k-conservative-from-broadqwen3-embedding-0.6b-lrat-full80k-hardneg-preserve-mr2-min6-from-broadadvisorai-qwen2.5-14b-stevensqwen3-embedding-0.6b-lrat-full80k-hardneg-preserve-mr2-min6-from-broad-singlefileqwen3-embedding-0.6b-lrat-annwinner-extrap-a125-soup-a50-v1llama-3.2-3b-taiwan-chat-ggufqwen3-embedding-0.6b-lrat-global256-utility-weighted-v1Llama-3.2-3B-Indonesian-Alpacaqwen14b-2wc1p-pj3ha_qwen14b-generic-eos-2Llama-3.2-3B-Indonesian-Alpaca-GRPOnaruto-gemma-2-9bOmniVoiceQwen2.5-3B-sft-think-indonesianllama1.2v1Qwen3-0.6B-planner-sftgemma-3-27b-it-abliterated-mlx-4Bitllama-3.1-8b-taiwan-chatqwen3vl-8b-chartqa-merged-16bit