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.
qwen2_5vl-7b-lora-sft-CoT_traineval_4epochs_mergedLlama-3.1-70B-LatamGPT-SFT-1.0Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2-GGUFOlmo-3-32B-Think-SFTQwen3-0.6B-Reverse-Text-SFTOlmo-3-7B-Instruct-SFTsft-sql-embeddingQwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2MiniCPM-2B-sft-bf16Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-GGUF-NInferqwen2.5-coder-32b-instruct-heretic-sft-i1-GGUFCodeLlama-13B-oasst-sft-v10-GGUFLlama-3.1-Tulu-3-8B-SFTCrPO-sft-llama-3.1-8b-instructOlmo-3-7B-Think-SFTQwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2GraphForge-Qwen3.6-35B-A3B-SFT-i1-GGUFLlama-3-8B-Magpie-Align-SFT-v0.3OLMo-2-0425-1B-SFTgemma-4-12b-it-roleplay-sft-epoch2-bf16-i1-GGUFsnowball-67b-a2b-sft-s3-nemotron-terminal-step1888GraphForge-Qwen3.6-27B-SFT-i1-GGUFMiniCPM5-2B-SFTOptiMind-SFTacestep-v15-xl-sftQwen3-1.7B-Wordle-SFTOLMo-2-1124-7B-SFTQwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2-GGUFLlama2-70B-OASST-SFT-v10-GGUFMiniCPM5-1B-SFT