Aiming to create the best quality quants for a Mac Studio 512GB
-
mlx-community/INTELLECT-3-8bit-gs32
Text Generation • 107B • Updated • 59 -
mlx-community/Kimi-Linear-48B-A3B-Instruct-mlx-bf16
Text Generation • 49B • Updated • 140 -
mlx-community/GLM-4.5-Air-mlx-8bit-gs32
Text Generation • 107B • Updated • 210 -
mlx-community/aquif-3.5-Max-42B-A3B-mlx-bf16
Text Generation • 42B • Updated • 147 • 2