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.
Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-MLX-mxfp8NVIDIA-Nemotron-3.5-Lightning-30B-A3B-mxfp8Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-MLX-mxfp8LFM2.5-2.6B-MLX-mxfp8LFM2.5-8B-A1B-MXFP8qwen3_5_9b_claude_4_6_highiq_instruct_heretic_uncensored_mxfp8Qwen3.5-27B-Uncensored-HauhauCS-Aggressive-MLX-mxfp8Qwen3.5-9B-Ultra-Heretic-MLX-mxfp8granite-4.2-30b-mxfp8-mlxQwen3.5-122B-A10B-Heretic-v2-MLX-mxfp8LFM2.5-230M-MXFP8Nemotron-3.5-Lightning-30B-A3B-MXFP8LFM2.5-2.6B-MXFP8Darwin-35B-A3B-Opus-MLX-mxfp8LFM2.5-2.6B-mxfp8granite-4.2-30b-mxfp8-mlxQwen3.6-35B-A3B-Heretic-MLX-mxfp8granite-4.2-8b-mxfp8-mlxgranite-4.2-8b-mxfp8-mlxNVIDIA-Nemotron-Labs-3-Elastic-12B-A2B-mxfp8-mlxMinistral-3-14B-Instruct-2512-mxfp8hy-mt2-1.8b-mxfp8-mlxgranite-4.2-3b-mxfp8-mlxCrow-9B-HERETIC-4.6-MLX-mxfp8Ministral-3-14B-Reasoning-2512-mlx-mxfp8gemma-4-12B-it-mxfp8-mlxQwen3.6-27B-Heretic-MLX-mxfp8granite-4.1-8b-mxfp8-mlxgemma-4-E4B-it-mxfp8-mlxLFM2.5-Embedding-350M-mxfp8
