Correct the activation figure: 14 GB is the 8192-token budget, not the 4096 default

README.md

@@ -31,9 +31,27 @@ Gated against the bf16 checkpoint and the PyTorch reference on the model's own
 | int8 vs bf16 MLX | 48/48 tokens identical |
 | final-position logits vs reference | cos 0.9982 (bf16 baseline: 0.9996) |
 
-Measured on an M5 Max (macOS 27): resident floor **5.0 GB** (bf16: 8.85), image-QA decode
-**88.3 tok/s** (bf16: 54.9). Activation memory is unchanged by quantization — budget
-~3 GB for a single image and ~14 GB for 16-frame video QA at a 4096-token budget.
+Measured on an M5 Max (macOS 27), one process per number, floor read post-load, at the default
+4096-token budget:
+
+| | resident floor | activation | decode |
+|---|---|---|---|
+| int8 · image | 5.0 GB | 3.0 GB | 85.7 tok/s |
+| int8 · video 16f | 5.0 GB | 5.8 GB | 80.0 tok/s |
+| bf16 · image | 8.85 GB | 2.85 GB | 51.2 tok/s |
+| bf16 · video 16f | 8.85 GB | 5.8 GB | 50.2 tok/s |
+
+Activation is unchanged by quantization (5.77 vs 5.79 GB) — only the resident floor moves.
+
+The **token budget**, not the frame count, is the memory lever: at a fixed budget, 32 frames
+costs slightly less than 16 because per-frame resolution drops to compensate. Raising the budget
+is what costs — the same clip at an 8192-token budget needs **14.2 GB** of activation.
+
+> **Corrected 2026-07-29.** This section previously read "~14 GB for 16-frame video QA at a
+> 4096-token budget". That 14 GB figure is real but belongs to the *8192*-token budget: it was
+> measured before per-frame video resolution was derived from the token budget, and was not
+> re-measured when the default changed. Swift package `v0.3.0` re-declares its footprint
+> accordingly.
 
 ## Use