From 6b651f6f8ef894f341db25ec792d3cb0d1009897 Mon Sep 17 00:00:00 2001 From: modelbeast Date: Fri, 17 Jul 2026 01:09:00 +1000 Subject: [PATCH] docs: intro reflects 5 machines --- docs/2026-07-16-m-series-fleet-ablation-results.md | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/docs/2026-07-16-m-series-fleet-ablation-results.md b/docs/2026-07-16-m-series-fleet-ablation-results.md index e7a6725..1f3ce2a 100644 --- a/docs/2026-07-16-m-series-fleet-ablation-results.md +++ b/docs/2026-07-16-m-series-fleet-ablation-results.md @@ -8,10 +8,11 @@ script: scripts/bench_optimizations.py (unmodified) + engine-level tiled×compil # M-series Fleet Ablation Benchmarks Same methodology as the 2026-03-09 wave2 doc (`--sweep ablation --resolution 512 1024 2048`, -checkpoint weights, 3 warmup + 10 bench runs), executed across four machines spanning the -Apple Silicon range — **M1 Ultra (64c) · M3 Ultra (80c) · M4 Pro mini 24GB · M5 MacBook Pro -16GB (10c)** — i.e. oldest→newest GPU generation and Studio→laptop. Contributed from a -multi-Mac render-farm setup; happy to run follow-ups on any of them. +checkpoint weights, 3 warmup + 10 bench runs), executed across **five machines** spanning the +Apple Silicon range — **M1 Ultra (64c) · M3 Ultra (80c) · M3 Air 16GB (10c, fanless) · M4 Pro +mini 24GB · M5 MacBook Pro 16GB (10c)** — i.e. every current GPU generation, Studio→fanless +laptop, and a matched-width M3-vs-M5 pair. Contributed from a multi-Mac render-farm setup; +happy to run follow-ups on any of them. ## Headline findings