diff --git a/apps/llama/configs/config.yaml b/apps/llama/configs/config.yaml
index 6f5fb40..17a2f9d 100644
--- a/apps/llama/configs/config.yaml
+++ b/apps/llama/configs/config.yaml
@@ -6,6 +6,7 @@ macros:
   base_args: "--no-warmup --port ${PORT}"
   common_args: "--fit-target 1536 --no-warmup --port ${PORT}"
   gemma3_ctx_128k: "--ctx-size 131072"
+  qwen35_ctx_128k: "--ctx-size 131072"
   qwen35_ctx_256k: "--ctx-size 262144"
   gemma_sampling: "--prio 2 --temp 1.0 --repeat-penalty 1.0 --min-p 0.00 --top-k 64 --top-p 0.95"
   qwen35_sampling: "--temp 0.6 --top-p 0.95 --top-k 20 --min-p 0.00 -ctk q8_0 -ctv q8_0"
@@ -163,7 +164,7 @@ models:
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-4B-GGUF:Q4_K_M
-        ${qwen35_ctx_256k}
+        ${qwen35_ctx_128k}
         ${qwen35_sampling}
         ${common_args}
         ${thinking_on}
@@ -172,7 +173,7 @@ models:
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-4B-GGUF:Q4_K_M
-        ${qwen35_ctx_256k}
+        ${qwen35_ctx_128k}
         ${qwen35_sampling}
         ${common_args}
         ${thinking_off}
@@ -182,7 +183,7 @@ models:
       /app/llama-server
         -hf mradermacher/Qwen3.5-4B-heretic-GGUF:Q4_K_M
         ${qwen35_4b_heretic_mmproj}
-        ${qwen35_ctx_256k}
+        ${qwen35_ctx_128k}
         ${qwen35_sampling}
         ${common_args}
         ${thinking_on}
@@ -192,7 +193,7 @@ models:
       /app/llama-server
         -hf mradermacher/Qwen3.5-4B-heretic-GGUF:Q4_K_M
         ${qwen35_4b_heretic_mmproj}
-        ${qwen35_ctx_256k}
+        ${qwen35_ctx_128k}
         ${qwen35_sampling}
         ${common_args}
         ${thinking_off}