AWQ-style pre-scaling using Unsloth's imatrix calibration data, then 3-6-bit affine quantization with the Unsloth mixed-precision recipe via MLX
-
Brooooooklyn/Qwen3.5-9B-unsloth-mlx
Text Generation • 2B • Updated • 2.76k • 10 -
Brooooooklyn/Qwen3.5-27B-unsloth-mlx
Text Generation • 6B • Updated • 3.29k • 15 -
Brooooooklyn/Qwen3.5-35B-A3B-UD-Q2_K_XL-mlx
Text Generation • 4B • Updated • 293 -
Brooooooklyn/Qwen3.5-35B-A3B-UD-Q3_K_XL-mlx
Text Generation • 6B • Updated • 342 • 1