remove gguf from mlx-swift build

[davidkoski]

See #110

From @awni

Hmm, we should build without GGUF support in MLX Swift / MLX C (MLX_BUILD_GGUF=OFF). We don't support it in the API anyway so it doesn't make sense to include it right?

[aPaleBlueDot]

Is there any way to bring in a Q4_1 quantized GGUF into MLX Swift? Or to specify q4_1 in mlx 's own quantization?

[aPaleBlueDot]

More broadly speaking, my use case requires quantizations other than the 2/4/8 bit options currently provided, especially Q3, Q5 and Q6 flavors. Are there any future plans to add more quantization options?