ai: unload llama's model from the engine row

The llama.cpp row offers Unload while a model is loaded. It posts to the
router's /models/unload, which frees the VRAM and leaves llama-server up,
so its web UI stays available; the engines themselves are still never
stopped from here. The answer is not read: the next poll shows the row
without a model, or with it if the unload failed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

1 files changed, 4 insertions, 1 deletions

diff --git a/desktop/modules/ai/AiPage.qml b/desktop/modules/ai/AiPage.qml
index e89132a..369c1b5 100644
--- a/desktop/modules/ai/AiPage.qml
+++ b/desktop/modules/ai/AiPage.qml
@@ -12,7 +12,8 @@
 import QtQuick
 import "../.."
 
-// Engines are read-only: stopping either would take its web UI down with it.
+// Engines are never stopped, that would take their web UI down with them;
+// llama's model can be unloaded, which frees the VRAM and leaves the server up.
 Column {
     id: page
 
@@ -42,6 +43,8 @@ Column {
                     return modelData.name === "llama" ? "No model loaded" : "Running";
                 return (modelData.busy ? "Generating" : "Idle") + " · " + modelData.model;
             }
+            action: modelData.name === "llama" && modelData.model !== "" ? "Unload" : ""
+            onTriggered: page.ai.unload(modelData.model)
         }
     }