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.
Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-GGUFSpark-X2.5-4B-MLX-8bitSpark-X2.5-4B-Q8_0-GGUFSpark-X2.5-4B-FP8L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-i1-GGUFSpark-X2.5-4B-INT8Spark-X2.5-4B-CRACK-JANG_8MLlama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-Q_6-MLXQwen3-4B-Element8-Eva-Xiaolong-Heretic-i1-GGUFL3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-GGUFXing4.0-29B-A4B-FP8Holo-3.1-4B-FP8-DynamicDolphin-X1-8B-mlx-4BitXing4.0-29B-A4B-MTDRSpark-X2.5-4B-JANG_8MLlama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-GGUFQwen3-4B-Element8-Eva-Xiaolong-Heretic-GGUFgpt4-x-alpaca-13b-native-4bit-128gLlama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLXQwen3.8-27B-GPTQ-Pro-FOEM-4bit-g128-ns256-INT8-Head-EmbeddingsXing4.0-29B-A4B-Official_Document_Writing_8kXing4.0-29B-A4B-8bit-MLXQwen3.5-4B-UD-Q8_K_XL.ggufDavidAU.L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit-GGUFQwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MLX-8bitSpark-X2.5-4B-Q8_0-GGUFSpark-X2.5-4B-MLX-8bitGemma-4-26B-A4B-IT-UD-Q8_K_XL-mlxLlama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-GGUFLlama-3.1-8B-bnb-4bit-Platon