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.
Qwen3.8-27B-3bit-MLX-TextOnlyQwen3.8-27B-2bit-MLX-TextOnlyQwen3.8-27B-4bit-MLX-TextOnlySONAR_200_text_decoderApertus-v1.5-8B-text-MLX-mxfp4Apertus-v1.5-70B-text-GGUFQwen3.6-27B-AEON-Ultimate-Uncensored-Text-NVFP4-MTP-XSApertus-v1.5-8B-text-MLX-5bitGemma-4-E2B-Uncensored-HauhauCS-Aggressive-Ollama-TextQwen3.8-27B-8bit-MLX-TextOnlyapertus-v1.5-8b-text-Q8_0-GGUFApertus-v1.5-8B-text-MLX-6bitQwen3.8-27B-6bit-MLX-TextOnlyQwen3.8-27B-5bit-MLX-TextOnlyQwen3.6-27B-AEON-Ultimate-Uncensored-Text-NVFP4-MTPApertus-v1.5-8B-text-MLX-4bit-DWQGemma-4-E4B-Uncensored-HauhauCS-Aggressive-Ollama-TextOrnith-1.5-35B-A3B-6bit-MLX-TextOnlyapertus-v1.5-8b-textGemma-4-E4B-it-TextOnly-GPTQ-SafetensorsApertus-v1.5-8B-text-MLX-8bitapertus-v1.5-8b-text-mlx-fp16Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggr-Ollama-TextBlind-Text-Modelsapertus-v1.5-8b-text-Q4_K_M-GGUFQwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlxOrnith-1.5-35B-A3B-3bit-MLX-TextOnlyOrnith-1.5-35B-A3B-8bit-MLX-TextOnlyQwen3.6-35B-A3B-Fable-Holo3.1-Text-1M-qx64-hi-mlxOrnith-1.5-35B-A3B-4bit-MLX-TextOnly