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.
GLM-4.6V-Flash-MLX-4bitMinistral-3-8B-Reasoning-2512-AWQ-4bitLFM2.5-1.2B-Instruct-MLX-4bitLFM2-24B-A2B-MLX-4bitQwopus3.6-27B-v2-AWQ-4bitGLM-OCR-4bitGLM-4.7-Flash-AWQ-4bitERNIE-4.5-21B-A3B-MLX-4bitMagistral-Small-2509-MLX-4bitMistral-Small-3.2-24B-Instruct-2506-MLX-4bitMinistral-3-14B-Instruct-2512-AWQ-4bitMinistral-3-3B-Instruct-2512-4bitDevstral-Small-2507-MLX-4bitDevstral-Small-2505-MLX-4bitQwen3.6-35B-A3B-Uncensored-Heretic-MLX-4bitGLM-5.3-Flash-MLX-4bit-MTPQwen3.5-27B-Claude-4.6-Opus-Distilled-MLX-4bitMistral-Nemo-Instruct-2407-4bitGLM-4.7-Flash-4bitLFM2.5-1.2B-Instruct-4bitQwen3-ASR-0.6B-MLX-4bitQwen3-ForcedAligner-0.6B-4bitQwen3.8-27B-Uncensored-OrcaRouter-MLX-4bitMinistral-3-3B-Instruct-2512-unsloth-bnb-4bitQwen-Image-Edit-2511-4bitQwen3.8-Flash-Next-Uncensored-REAP288-MTP-MLX-4bitDevstral-Small-2507-AWQ-4bitMiniCPM5-1B-OptiQ-4bitMiniCPM5-2B-mlx-4BitGLM-4.7-Flash-MLX-4bit
