From 8d1e70bb7da4378e382de59da7d518b83e4842e9 Mon Sep 17 00:00:00 2001
From: Holden Salomon <holden@arch.fyi>
Date: Fri, 12 Jun 2026 17:00:11 +0000
Subject: [PATCH] docs: correct CPU embedding speed estimate (tens of seconds,
 not minutes)

---
 Troubleshooting.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Troubleshooting.md b/Troubleshooting.md
index 4d8b3df..1dfa8fe 100644
--- a/Troubleshooting.md
+++ b/Troubleshooting.md
@@ -61,7 +61,7 @@ winnow downloads InsightFace and HuggingFace (SigLIP) models on first run.
 
 Use the `:cpu` image tag (`ghcr.io/sudolulo/winnow:cpu`) which omits the CUDA base entirely. Or set `FORCE_CPU=true` with `:latest` to disable GPU at runtime.
 
-Everything works on CPU but embedding computation is slower — expect several minutes per person instead of seconds.
+Everything works on CPU but embedding computation is slower — typically tens of seconds per person instead of under a second on GPU.
 
 If you have a GPU but it's not being used:
 - Confirm the NVIDIA container toolkit is installed: `docker run --rm --gpus all nvidia/cuda:13.3.0-base-ubuntu22.04 nvidia-smi`