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-Coder-30B-A3B-Instruct-MLX-5bitLFM2-24B-A2B-MLX-5bitQwen3-4B-Instruct-2507-MLX-5bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-5bitSeed-OSS-36B-Instruct-MLX-5bitQwen3-Next-80B-A3B-Instruct-MLX-5bitQwen3.8-9B-heretic-uncensored-5bit-MLXbitnet_b1_58-largeQwen3.8-9B-Distill-mlx-5BitGLM-4.7-Flash-5bitGLM-5.3-mixed-4_5bitbitnet_b1_58-3BGLM-5.3-5bit-UVMAXQwen3-Coder-Next-5bitGLM-5.3-MLX-5bitQwen3.8-2B-Distill-mlx-5BitNVIDIA-Nemotron-3-Super-120B-A12B-5bitOrnith-1.0-9B-MLX-5bitApertus-v1.5-8B-text-MLX-5bitQwen3.6-35B-A3B-MTP-5bitOrnith-1.0-35B-MLX-5bitQwen3.8-27B-5bit-MLX-TextOnlyGLM-5.2-MLX-5bitLFM2.5-2.6B-MLX-5bitApodex-1.1-mini-MLX-5bitbitnet_b1_58-xl_q8_0_ggufQwen3.8-9B-mlx-5BitLaguna-XS-2.1-MLX-5bitHuihui-Ornith-1.5-9B-abliterated-mlx-5BitFastino-Nemotron-3.5-Lightning-Healthcare-MLX-5bit
