LTX-2.5 on 16GB Mac Mini M4: My ComfyUI Solution Explained 🔥 How It Actually Works

[Dev_Raj]

For visual reference and step-by-step node execution showing peak tensor handling and VAE decoding on 16GB UMA (mps⁠, ⁠memory⁠, ⁠diffusion⁠, and ⁠mac⁠) on Mac mini m4 16gb Ram with extended VRAM.

export PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0

I recorded the complete workflow walkthrough here: https://youtu.be/OuxRE4m8PU8