diff --git a/kubernetes/apps/ai/llmkube/models/qwen3-embedding.yaml b/kubernetes/apps/ai/llmkube/models/qwen3-embedding.yaml
index 4c5a584b4..2c761d920 100644
--- a/kubernetes/apps/ai/llmkube/models/qwen3-embedding.yaml
+++ b/kubernetes/apps/ai/llmkube/models/qwen3-embedding.yaml
@@ -36,7 +36,7 @@ spec:
   # Native upstream GTT-leak mitigation in LLMKube >=0.9.10; lifetime includes
   # startup and model load before this Vulkan embedder is recycled.
   maxPodLifetimeSeconds: 86400
-  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:31bca24d4ecd1ee8decae5d626ae833bb5d34b94ba9d2f308e7cedcd6bb3e247
+  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:5b69b5a99886b6bdc24c281b9a041c21e0e9d5502018c55098d4b09cac6ee5a4
   # Two slots are the Vulkan-safe floor; more interleaving did not improve
   # throughput on this compute-bound iGPU. VMCP has its own embedder now.
   parallelSlots: 2 # Vulkan warmup hangs at parallel=1 (llama.cpp #24307)
diff --git a/kubernetes/apps/ai/llmkube/models/qwen35-2b.yaml b/kubernetes/apps/ai/llmkube/models/qwen35-2b.yaml
index 1288c4bd0..5c245856b 100644
--- a/kubernetes/apps/ai/llmkube/models/qwen35-2b.yaml
+++ b/kubernetes/apps/ai/llmkube/models/qwen35-2b.yaml
@@ -33,7 +33,7 @@ spec:
   modelRef: qwen35-2b
   # Must be recent enough for Qwen3.5's GDN (Gated Delta Networks) architecture;
   # verified to load `qwen35` and run GDN fully on Vulkan (no CPU fallback).
-  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:31bca24d4ecd1ee8decae5d626ae833bb5d34b94ba9d2f308e7cedcd6bb3e247
+  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:5b69b5a99886b6bdc24c281b9a041c21e0e9d5502018c55098d4b09cac6ee5a4
   parallelSlots: 2 # Vulkan warmup hangs at parallel=1 (llama.cpp #24307)
   contextSize: 16384 # GDN keeps KV tiny, so long ctx is cheap; 16K is plenty for offload
   jinja: true # use the model's chat template (correct Qwen3.5 formatting + tool calls)
diff --git a/kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml b/kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml
index f106adb21..9fc45b5f8 100644
--- a/kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml
+++ b/kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml
@@ -42,7 +42,7 @@ spec:
   # Native upstream GTT-leak mitigation in LLMKube >=0.9.10; lifetime includes
   # startup and model load before this Vulkan embedder is recycled.
   maxPodLifetimeSeconds: 86400
-  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:31bca24d4ecd1ee8decae5d626ae833bb5d34b94ba9d2f308e7cedcd6bb3e247
+  image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:5b69b5a99886b6bdc24c281b9a041c21e0e9d5502018c55098d4b09cac6ee5a4
   # Vulkan floor is 2 — warmup hangs at parallel=1 (llama.cpp #24307). The iGPU
   # is compute-bound, so more slots add interleave, not throughput.
   parallelSlots: 2