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.
LFM2-24B-A2B-MLX-5bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-5bitQwen3.8-9B-heretic-uncensored-5bit-MLXQwen3.8-9B-Distill-mlx-5BitGLM-4.7-Flash-5bitGLM-5.3-mixed-4_5bitGLM-5.3-5bit-UVMAXNVIDIA-Nemotron-3-Super-120B-A12B-5bitQwen3.6-35B-A3B-MTP-5bitQwen3.8-2B-Distill-mlx-5BitLFM2.5-2.6B-MLX-5bitQwen3.8-9B-mlx-5BitFluko-Nano-1B-Exp-MLX-5bitKimi-K2-Instruct-0905-MLX-5bitHermes-4-405B-MLX-5bitzeta-2.1-5bitgranite-4.2-8b-5bit-mlxLFM2.5-8B-A1B-MLX-5bitHermes-4.3-36B-mlx-5BitLFM2.5-1.2B-Thinking-MLX-5bitLFM2.5-2.6B-MLX-5bitgranite-4.2-3b-5bit-mlxEquinox-31B-5bitLFM2.5-1.2B-Instruct-MLX-5bitQwen3.5-9B-MTP-5bitgranite-4.2-30b-5bit-mlxLFM2.5-1.2B-JP-MLX-5bitLFM2.5-1.2B-JP-202606-MLX-5bitLFM2.5-350M-MLX-5bitLFM2.5-230M-MLX-5bit