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 **0.091 seconds** to generate a token
+### Performance Test
+
+After several executions on a *Nvidia T4 with 16GB VRAM*, we got: it takes aprox **0.091 seconds** to generate a token
+
+| Latency | GPU Mem |
+----------|---------|
+|43.36ms/token | 3.83 GB |