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.
Qwen3.8-27B-MLX-5bitgemma-4-E4B-it-MLX-5bitQwen3.6-27B-MLX-5bitgemma-4-12B-it-MLX-5bitgemma-4-E2B-it-MLX-5bitQwen3-VL-8B-Instruct-MLX-5bitgemma-4-26B-A4B-it-MLX-5bitQwen3-Coder-30B-A3B-Instruct-MLX-5bitgemma-4-31B-it-MLX-5bitQwen3-VL-4B-Instruct-MLX-5bitLFM2-24B-A2B-MLX-5bitHermes-4-70B-MLX-5bitQwen3-4B-Instruct-2507-MLX-5bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-5bitQwen3-VL-30B-A3B-Instruct-MLX-5bitSeed-OSS-36B-Instruct-MLX-5bitMagistral-Small-2509-MLX-5bitbit-50Qwen3-Next-80B-A3B-Instruct-MLX-5bitQwen3.8-27B-MLX-5bitQwen3.8-9B-heretic-uncensored-5bit-MLXbitnet_b1_58-largeQwen3.8-9B-Distill-mlx-5Bitbitnet_b1_58-large-TQ2_0resnetv2_50x1_bit.goog_in21k_ft_in1kQwen3.6-35B-A3B-5bitGLM-4.7-Flash-5bitresnetv2_50x1_bit.goog_in21kalbedo-qwen3.6-35b-v555Qwen3.8-27B-Uncensored-OrcaRouter-MLX-5bit
