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.
gpt-oss-20b-RichardErkhov-heresyQwen3-14B-abliterated-GGUFQwen2.5-7B-Instruct-abliterated-GGUFCardinalOperations_-_ORLM-LLaMA-3-8B-ggufqwen3.5-4b-reduction-coldstartTechxGenus_-_CursorCore-QW2.5-1.5B-ggufTechxGenus_-_CursorCore-QW2.5-1.5B-SR-ggufTechxGenus_-_CursorCore-Yi-1.5B-SR-ggufQwen3-4B-Instruct-2507-hereticgpt-oss-20b-RichardErkhov-heresy-GGUFLlama-3.1-8B-Instruct-abliterated-obliteratusKimi-K2-Instruct-0905-MLX-2bitKimi-K2-Instruct-0905-MLX-4bitmythos-9b-unhinged-abliterated-mlxKimi-K2-Instruct-0905-MLX-8bitTechxGenus_-_CursorCore-DS-1.3B-ggufKimi-K2-Instruct-0905-MLX-6bitKimi-K2-Instruct-0905-MLX-3bitKimi-K2-Instruct-0905-MLX-5bitrichard-park-llama-3-8B-inst-unsloth-ko-merged-1-GGUFrichmondsin-finetuned-gemma-2-2b-output-layer-20-16k-4-GGUFrichmondsin-finetuned-gemma-2-2b-output-layer-20-4k-7-GGUFrichmondsin-finetuned-gemma-2-2b-output-layer-20-4k-3-GGUFMythos-nano-hereticQwen3-8B-Abliteratedqwen3-32buigen-x-30b-moeDeepseek-R1-Distill-Qwen-32b-uncensoredtiny-qwen3-30m-zhtiny-qwen3-30m