diff --git a/qai_hub_models/models/llama_v2_7b_chat_quantized/perf.yaml b/qai_hub_models/models/llama_v2_7b_chat_quantized/perf.yaml
index e62b8e66..19c64c6c 100644
--- a/qai_hub_models/models/llama_v2_7b_chat_quantized/perf.yaml
+++ b/qai_hub_models/models/llama_v2_7b_chat_quantized/perf.yaml
@@ -36,7 +36,7 @@ models:
     timestamp: '2024-05-23T00:34:02.549319Z'
     torchscript_onnx_qnn:
       inference_time: 1917811
-      throughput: 0.5214
+      throughput: 533.94
       estimated_peak_memory_range:
         min: 20480
         max: 1078248176