diff --git a/model-engine/model_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py b/model-engine/model_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py
index 3668a8959..9e94859a9 100644
--- a/model-engine/model_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py
+++ b/model-engine/model_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py
@@ -399,7 +399,7 @@ async def create_text_generation_inference_bundle(
         max_input_length = 1024
         max_total_tokens = 2048
         if "llama-2" in model_name:
-            max_input_length = 2048
+            max_input_length = 4095
             max_total_tokens = 4096
 
         subcommands = []