From 4ec72fa8f49ae040c65cfaf2bb0c83f801bd93ee Mon Sep 17 00:00:00 2001
From: "S. Neuhaus" <neuhaus@users.noreply.github.com>
Date: Thu, 30 Oct 2025 18:11:28 +0100
Subject: [PATCH] Fix command syntax for llama-cli usage

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

diff --git a/README.md b/README.md
index 97769b1..b5ae284 100644
--- a/README.md
+++ b/README.md
@@ -145,7 +145,7 @@ Once inside, the following commands show how to run local LLMs:
 
 * `llama-cli --list-devices`
   *Lists available GPU devices for Llama.cpp.*
-* `llama-cli --no-mmap -ngl 999 -fa -m <model>`
+* `llama-cli --no-mmap -ngl 999 -fa 1 -m <model>`
   *Runs inference on the specified model, with all layers on GPU and flash attention enabled (replace \*\* with your model path).*
 
 ## 2.3 Downloading GGUF Models from HuggingFace