llama-server: models-max 2 -> 3

Three residents (Laguna ~64G + ornith-1.5-35b ~21G + qwen3-vl-8b ~6G)
fit the ~104G TTM window with KV headroom. Needed now that both Hermes
hosts run their main loops off the router: straylight (laguna-s-2.1)
and talos (ornith-1.5-35b-a3b) each want a resident slot, leaving the
VLM as the third.

Working-tree WIP (nix-ld libs for hermes desktop) intentionally left
uncommitted.

hw/straylight/default.nix

@@ -224,7 +224,7 @@ in
             --host 0.0.0.0 \
             --port 11434 \
             --models-preset ${llamaModelsIni} \
-            --models-max 2 \
+            --models-max 3 \
             --timeout 7200
         '';
         User = "llama-server";