Aiming to create the best quality quants for a single Mac Studio 512GB
-
mlx-community/Kimi-K2.5-mlx-DQ3_K_M-q8
Text Generation • 1T • Updated • 1.37k • 2 -
mlx-community/Qwen3.5-397B-A17B-8bit-gs32
Text Generation • 396B • Updated • 311 -
mlx-community/MiniMax-M2.5-8bit
Text Generation • 229B • Updated • 5.05k • 2 -
mlx-community/MiniMax-M2.5-3bit
Text Generation • 229B • Updated • 1.69k • 9