Card: whole-process peak memory and --low-memory (pjit-mlx 0.1.1)

README.md

@@ -12,7 +12,7 @@ This is an MLX export of [Linum-AI/pjit-21k](https://huggingface.co/Linum-AI/pji
 text-to-image DiT. It comes with its Qwen3.5-4B caption encoder, trimmed to the 28 blocks the model reads. The runner
 is [pjit-mlx](https://github.com/felix-ab/pjit-mlx).
 
-**Tier:** 8-bit (compact: 3.6 GB peak). It is as clean as bf16 at 100% and usually gives the same picture for a seed
+**Tier:** 8-bit (compact: 3.6 GB peak for the whole process with `--low-memory`, 5.0 GB without). It is as clean as bf16 at 100% and usually gives the same picture for a seed
 (14 of 15 gallery tests, with more fine-detail drift), but it can fork on sensitive prompts.
 
 ![Eight renders from this tier, made on an M4 Pro from prompts and seeds in Linum's gallery](assets/gallery.jpg)
@@ -22,12 +22,15 @@ is [pjit-mlx](https://github.com/felix-ab/pjit-mlx).
 | M4 Pro, one 1152×864 image, 50 steps | This tier | PyTorch on MPS |
 |---|---|---|
 | Total time | 79 s | 139 s |
-| Peak memory | 3.6 GB | 14.9 GB |
+| Peak memory, whole process | 5.0 GB; 3.6 GB with `--low-memory` | 14.9 GB |
 | Download | 6.9 GB | 18.0 GB |
 
+Peak memory is the process's peak physical footprint as macOS reports it, the same meter in both columns.
+`--low-memory` evaluates the DiT block by block and caps MLX's buffer cache; the pixels are identical.
+
 ```bash
 pip install git+https://github.com/felix-ab/pjit-mlx
-pjit-mlx --tier 8bit --seeds 4 --aspect 4:3 \
+pjit-mlx --tier 8bit --low-memory --seeds 4 --aspect 4:3 \
   --prompt "Bright midday sun lights a white man in his thirties in a head-and-shoulders portrait, squinting slightly with a relaxed half smile. His faded blue chambray shirt is open at the collar, and a field of tall grass blurs behind him."
 ```