llama-server: revert models-max 3 -> 2 (OOM-killed desktop on rebuild)

models-max 3 pulled all three residents into RAM and the OOM killer took the desktop (and Hermes) mid-switch. models-max 2 is the safe baseline; co-residency of all three is a future-optimization, not a today one.
2026-09-19 21:51:50 -07:00
parent 0543864f38
commit a893514708
1 changed files with 1 additions and 1 deletions
@@ -227,7 +227,7 @@ in
            --host 0.0.0.0 \
            --port 11434 \
            --models-preset ${llamaModelsIni} \
-            --models-max 3 \
+            --models-max 2 \
            --timeout 7200
        '';
        User = "llama-server";