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/Qwen3.6-35B-A3B-UD-Q2_K_XL-mlx
Text Generation • 4B • Updated • 1.31k • 3 -
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q3_K_XL-mlx
Text Generation • 6B • Updated • 1.04k • 4 -
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q4_K_XL-mlx
Text Generation • 7B • Updated • 5.61k • 8 -
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q5_K_XL-mlx
Text Generation • 8B • Updated • 663 • 1