[Template Bug]: z-image template generates noisy black image

### Confirmation

- [x] I have confirmed this is a workflow template mistake

### Template Name

image_z_image_turbo

### Problem Description

I’m running ComfyUI v0.5 on an M4 16GB MacBook Air, using GGUF models of z-image-turbo and Qwen3-4 for fast inference.

However, I’ve noticed that z-image-turbo-Q4_K_M/S produces noisy outputs—though it works perfectly on my NVIDIA GPU-equipped PC. Only the Q3 quantized version runs reliably on macOS.

### ComfyUI Mode

Legacy Mode

### Error Message / Logs

```text
no error

loaded completely; 95367431640625005117571072.00 MB usable, 159.87 MB loaded, full load: True
Prompt executed in 327.71 seconds
got prompt
gguf qtypes: F32 (245), F16 (24), Q4_K (150), Q5_K (30), BF16 (4)
model weight dtype torch.bfloat16, manual cast: None
model_type FLOW
unet missing: ['norm_final.weight']
Requested to load Lumina2
loaded completely; 95367431640625005117571072.00 MB usable, 4526.45 MB loaded, full load: True
0%| | 0/9 [00:00

Start with the image_z_image_turbo workflow and review the reported logs for the z-image-turbo-Q4_K_M/S runs on the M4 MacBook Air. Compare the workflow behavior with the Q3 quantized version and the NVIDIA run; done means the affected quantizations produce a non-noisy image on macOS.

Written by the indexing model from the issue text.