Update README.md

README.md

@@ -42,7 +42,8 @@ This is a new-old-stock version of the model, with embeddings at 6 bit.
 The original [Qwen3-Yoyo-V3-54B-A3B-Thinking-TOTAL-RECALL-qx86-hi-mlx](https://huggingface.co/nightmedia/Qwen3-Yoyo-V3-54B-A3B-Thinking-TOTAL-RECALL-qx86-hi-mlx) is using 4 bit embeddings
 
 ```bash
-
+Perplexity: 5.291 ± 0.037
+Peak memory: 53.16 GB
 ```
 
 Metrics coming soon. If this proves better than the qx86-hi, it will replace it in the catalog.