diff --git a/services/vllm/config_llama.yaml b/services/vllm/config_llama.yaml
index 1a44e59..de48363 100644
--- a/services/vllm/config_llama.yaml
+++ b/services/vllm/config_llama.yaml
@@ -2,8 +2,8 @@ model: meta-llama/Llama-3.1-8B-Instruct
 host: "0.0.0.0"
 port: 8001
 uvicorn-log-level: "info"
-gpu-memory-utilization: 0.95
-max-model-len: 32768
+gpu-memory-utilization: 0.80
+max-model-len: 24576
 dtype: auto
 enforce-eager: false
 enable-auto-tool-choice: true