diff --git a/dev-llama-3-large.yaml b/dev-llama-3-large.yaml
index 9029eedc2d0b90931c77644beb1d61a7187ae7d2..a2c52eb1adcc2adb6e1741d63ad2290fa84e787d 100644
--- a/dev-llama-3-large.yaml
+++ b/dev-llama-3-large.yaml
@@ -9,7 +9,7 @@ config_file: |
   f16: true 
   gpu_layers: 85
   parameters:
-    model: downloads/llama_backend/Llama-3.1-Nemotron-70B-Instruct-HF-Q6_K 
+    model: downloads/llama_backend/Llama-3.1-Nemotron-70B-Instruct-HF-Q6_K.gguf 
   
   template:
     chat_message: |