Update README.md

README.md

@@ -136,5 +136,10 @@ instruction = "Dame una lista de lugares a visitar en España."
 print(generate(instruction))
 ```
 
-## Benchmark
-Running the model on a *Nvidia T4 with 16GB VRAM*, it takes aprox **0.15 seconds** to generate a token
+### Performance Test
+
+After several executions on a *Nvidia T4 with 16GB VRAM*, we got:
+
+| Latency | GPU Mem Required |
+----------|---------|
+|49.39 ms/token | 7.06 GB |