Add qwen3.5:27b to Ollama and bump memory limit to 22Gi

The 27B Q4_K_M model is ~17 GB, exceeding the 16 GB VRAM on the RTX 4080
by ~1 GB. Ollama will offload a few layers to CPU RAM, so the pod memory
limit needs headroom beyond the previous 16Gi.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

argocd/manifests/ollama/deployment.yaml

@@ -40,7 +40,7 @@ spec:
               memory: "512Mi"
               cpu: "500m"
             limits:
-              memory: "16Gi"
+              memory: "22Gi"
               cpu: "4000m"
               nvidia.com/gpu: "1"
           livenessProbe:

argocd/manifests/ollama/models.txt

@@ -5,3 +5,4 @@ deepseek-r1:14b
 phi4:14b
 gemma3:12b
 qwen3.5:9b
+qwen3.5:27b