From d777b8a0290cced0064eb5f503a25b65b148c1bc Mon Sep 17 00:00:00 2001
From: Arcitec <38923130+Arcitec@users.noreply.github.com>
Date: Thu, 11 Sep 2025 07:06:25 +0200
Subject: [PATCH] docs: Add FP16 usage advice for faster inference

---
 README.md | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index b77a31c..c5076ca 100644
--- a/README.md
+++ b/README.md
@@ -264,7 +264,10 @@ uv run webui.py -h
 Have fun!
 
 > [!IMPORTANT]
-> **DeepSpeed** *may* speed up inference on some systems, but it could also
+> It can be very helpful to use **FP16** (half-precision) inference. It is faster
+> and uses less VRAM, with a very small quality loss.
+> 
+> **DeepSpeed** *may* also speed up inference on some systems, but it could also
 > make it slower. The performance impact is highly dependent on your specific
 > hardware, drivers and operating system. Please try with and without it,
 > to discover what works best on your personal system.