Low VRAM Mode Model Loading Crash Since ComfyUI v0.3.51 (Including v0.3.57)

### Custom Node Testing

- [x] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

Using split attention in VAE
Using split attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.float16
Using scaled fp8: fp8 matrix mult: False, scale input: False
Requested to load QwenImageTEModel_
loaded completely 9.5367431640625e+25 7263.013442993164 True
CLIP/text encoder model load device: cpu, offload device: cpu, current: cpu, dtype: torch.float16
FETCH ComfyRegistry Data: 75/96
FETCH ComfyRegistry Data: 80/96
FETCH ComfyRegistry Data: 85/96
model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16
model_type FLUX
FETCH ComfyRegistry Data: 90/96
FETCH ComfyRegistry Data: 95/96
Requested to load QwenImage
FETCH ComfyRegistry Data [DONE]
[ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
[ComfyUI-Manager] All startup tasks have been completed.

### Actual Behavior

Using split attention in VAE
Using split attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.float16
Using scaled fp8: fp8 matrix mult: False, scale input: False
Requested to load QwenImageTEModel_
loaded completely 9.5367431640625e+25 7909.737449645996 True
CLIP/text encoder model load device: cpu, offload device: cpu, current: cpu, dtype: torch.float16
FETCH ComfyRegistry Data: 10/96
FETCH ComfyRegistry Data: 15/96
FETCH ComfyRegistry Data: 20/96
FETCH ComfyRegistry Data: 25/96
model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16
model_type FLUX
FETCH ComfyRegistry Data: 30/96
Killed

### Steps to Reproduce

1. git checkout 0.3.57
2. python main.py --lowvram --disable-all-custom-nodes
3. attempt to load a model
4. comfyui process is killed

### Debug Logs

```powershell
Using split attention in VAE
Using split attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.float16
Using scaled fp8: fp8 matrix mult: False, scale input: False
Requested to load QwenImageTEModel_
loaded completely 9.5367431640625e+25 7909.737449645996 True
CLIP/text encoder model load device: cpu, offload device: cpu, current: cpu, dtype: torch.float16
FETCH ComfyRegistry Data: 10/96
FETCH ComfyRegistry Data: 15/96
FETCH ComfyRegistry Data: 20/96
FETCH ComfyRegistry Data: 25/96
model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16
model_type FLUX
FETCH ComfyRegistry Data: 30/96
Killed
```

### Other

AMD GPU 9070xt

```
Name: gfx1201
Marketing Name: AMD Radeon RX 9070 XT
Vendor Name: AMD
Feature: KERNEL_DISPATCH
Profile: BASE_PROFILE
Float Round Mode: NEAR
Max Queue Number: 128(0x80)
Queue Min Size: 64(0x40)
Queue Max Size: 131072(0x20000)
Queue Type: MULTI
```