diff --git a/Makefile b/Makefile
index d6e0613b..65614583 100644
--- a/Makefile
+++ b/Makefile
@@ -5,7 +5,7 @@ BINARY_NAME=local-ai
 
 # llama.cpp versions
 GOLLAMA_STABLE_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be
-CPPLLAMA_VERSION?=628b299106d1e9476fdecb3cbe546bf5c60f1b89
+CPPLLAMA_VERSION?=858f6b73f6e57a62523d16a955d565254be889b4
 
 # gpt4all version
 GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all