Enable CPU vision projector for Ultra profile

compose.yaml

@@ -394,9 +394,8 @@ services:
       - --spec-draft-type-v
       - f16
 
-  # Text-only maximum-context profile. This exact IQ4_XS-pure / 256K / 80:20
-  # combination completed the 220K fill test on RTX 5080 + RTX 3060.
-  # Deliberately no vision projector: Ultra prioritizes maximum usable context.
+  # Maximum-context profile. Keep the vision projector on CPU so images work
+  # without consuming the tightly budgeted GPU memory of the 256K context.
   llama-ultra:
     <<: *llama-common
     container_name: mike-ai-llama-ultra
@@ -408,6 +407,9 @@ services:
     command:
       - --model
       - "/models/${ULTRA_MODEL_FILE:?ULTRA_MODEL_FILE is required}"
+      - --mmproj
+      - "/models/${VISION_PROJECTOR_FILE:?VISION_PROJECTOR_FILE is required}"
+      - --no-mmproj-offload
       - --alias
       - qwen-ultra
       - --ctx-size