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.
JoyAI-LLM-Flash-MXFP8-last-6-BF16Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-MLX-mxfp8Qwen3.8-27B-MXFP8Qwen3.8-27B-MXFP8-CRACKQwen3.8-27B-MTP-mxfp8Qwen3.6-27B-Coder-uncensored-MXFP8Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-Fable-mxfp8-mlxOrnith-1.5-35B-A3B-UNCENSORED-MXFP8Qwopus3.8-27B-Flash-mxfp8-MLXqwopus3.8-27b-flash-abliterated-mxfp8-vision-mtplxOrnith-1.5-9B-MXFP8gemma-4-12B-it-MXFP8Qwen3.8-27B-Brainwaves-mxfp8-mlxOrnith-1.5-35B-A3B-MXFP8NVIDIA-Nemotron-3.5-Lightning-30B-A3B-mxfp8Qwen3.8-27B-Cold-Fusion-FF711-Darker-Hero-GAIN-B-mxfp8-mlxBAAI-bge-reranker-v2-m3-mlx-mxfp8-8bitGLM-5-8bit-MXFP8Ornith-1.5-35B-A3B-mlx-mxfp8Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-mxfp8-mlx-mlx-4BitQwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-MLX-mxfp8LFM2.5-2.6B-MLX-mxfp8Qwen3.5-27B-Claude-4.6-OS-INSTRUCT-mxfp8-mlxgemma-4-31B-it-qat-mxfp8OmniCoder-9B-mlx-mxfp8gemma-4-31B-Claude-Opus-Distill-abliterated-mlx-mxfp8Qwen3.5-9B-Continuum-mxfp8-mlxQwen3.6-27B-GrandWichtel-mxfp8-mlxWichtelchen-Qwen3.5-9B-mxfp8-mlxLFM2.5-8B-A1B-MXFP8
