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.
Apertus-8B-Instruct-2509Qwen3.8-27B-NVFP4-MTP-GGUFbge-reranker-v2.5-gemma2-lightweightbge-reranker-v2-gemmaApertus-70B-2509qwen3.8-27b-abliterated-3.69bpw-12GB-MTP.ggufQwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4Qwen3.8-27B-GSQ-RCO-IQ3_XXS-UncensoredApertus-70B-Instruct-2509Gemma-4-26B-A4B-it-NVFP4Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NVFP4-GGUFQwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-NVFP4-GGUFApertus-8B-2509Qwen3.6-27B-V2-abliterated-uncensored-Q4_K_M-GGUFQwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16SeaLLM-7B-v2Qwen3.8-27B-MIX_GGUFSeaLLM-7B-v2.5gemma-4-E2B-it-qat-q4_0-heretic-GGUFQwen3.8-27B-AEON-ULTIMATE-UNCENSORED-NVFP4-MIXEDQwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTPQwen3.8-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASSQwen3.8-27B-3bit-MLX-TextOnlyQwen3.8-27B-NVFP4-BUDGET-GGUFQwen3.8-27B-Brainwaves-WFH-BF16-i1-GGUFParam2-17B-A2.4B-ThinkingLFM2.5-2.6B-Heretic-Abliterated-GGUFQwen3.8-27B-ColdFusion-GAIN-Blackwell-DFlash2-Ultra-V1.0Whittle-Next-27B-A3B-GGUFWhittle-Next-27B-A3B
