From d488d874900325057651002900d5afbd22545100 Mon Sep 17 00:00:00 2001
From: m3ultra <m3ultra@m3ultra.local>
Date: Sun, 19 Jul 2026 12:51:24 +1000
Subject: [PATCH] benchmarks: Hunyuan mlx-tune e2e 246s vs 260s baseline
 (~1.06x, texture-led)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---
 BENCHMARKS.md | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/BENCHMARKS.md b/BENCHMARKS.md
index c330595..c5848d2 100644
--- a/BENCHMARKS.md
+++ b/BENCHMARKS.md
@@ -227,3 +227,12 @@ control (running) decides. fal renders clean with the same weights, so the
 attrs are likely fine → Metal sampling is the prime suspect.
 
 Caveat: 75 GB peak fits both Ultras but check m1 headroom under load.
+
+## 2026-07-19 — Hunyuan mlx-tune e2e (T1+T3+T4, HY3D_MLX_COMPILE=1, m3ultra)
+
+anatomy bench image, defaults (50 steps, octree 256): shape 146s + tex 101s
+= **246s total, 17.5GB peak** vs recorded defaults baseline 260s (149+112).
+≈ **1.06× e2e** — texture stage carries the win (112→101s = T4 fused DINO
++ T1 UNet compile); shape delta noise-level. Caveat: baseline row used a
+different input image; same settings though. Next lever: Target 2
+whole-DiT compile (unblocked by T3).