diff --git a/apps/llama/configs/config.yaml b/apps/llama/configs/config.yaml
index 7707125..3485469 100644
--- a/apps/llama/configs/config.yaml
+++ b/apps/llama/configs/config.yaml
@@ -4,11 +4,11 @@ logToStdout: "both" # proxy and upstream
 
 macros:
   base_args: "--no-warmup --port ${PORT} --mlock --no-mmap"
-  common_args: "--fit-target 1536 --no-warmup --port ${PORT} --no-mmap"
+  common_args: "--fit-target 256 --no-warmup --port ${PORT} --no-mmap -tb 12 -t 6"
   cpu_args: "--no-warmup --port ${PORT} -ngl 0"
   ctx_64k: "--ctx-size 65536"
   ctx_128k: "--ctx-size 131072"
-  ctx_256k: "--ctx-size 262144"
+  ctx_256k: "--ctx-size 131072"
   qwen35_think_args:   "--temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.00 -ctk q4_0 -ctv q4_0 --presence_penalty 1.5 --reasoning on"
   qwen35_nothink_args: "--temp 0.7 --top-p 0.80 --top-k 20 --min-p 0.00 -ctk q4_0 -ctv q4_0 --presence_penalty 1.5 --reasoning off"
   qwen35_35b_heretic_mmproj: "--mmproj-url https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF/resolve/main/mmproj-F16.gguf --mmproj /root/.cache/llama.cpp/unsloth_Qwen3.5-35B-A3B-GGUF_mmproj-F16.gguf"
diff --git a/apps/llama/deployment.yaml b/apps/llama/deployment.yaml
index b05d1db..2c73135 100644
--- a/apps/llama/deployment.yaml
+++ b/apps/llama/deployment.yaml
@@ -18,7 +18,7 @@ spec:
     spec:
       initContainers:
         - name: download-whisper
-          image: gitea.lumpiasty.xyz/lumpiasty/llama-swap:unified-vulkan-test
+          image: gitea.lumpiasty.xyz/lumpiasty/llama-swap:unified-vulkan-b9222
           command:
             - sh
             - -c
@@ -48,7 +48,7 @@ spec:
               mountPath: /root/.cache
       containers:
         - name: llama-swap
-          image: gitea.lumpiasty.xyz/lumpiasty/llama-swap:unified-vulkan-test
+          image: gitea.lumpiasty.xyz/lumpiasty/llama-swap:unified-vulkan-b9222
           imagePullPolicy: IfNotPresent
           command:
             - llama-swap