Update README.md

README.md

@@ -40,7 +40,21 @@ pipeline_tag: text-generation
 
 # Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-II-qx86x-hi-mlx
 
-This model [Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-II-qx86x-hi-mlx](https://huggingface.co/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-II-qx86x-hi-mlx) was
+This is a new-old-stock version of the model, with embeddings at 8 bit.
+
+The original [Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-II-qx86-hi-mlx](https://huggingface.co/nightmedia/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-II-qx86-hi-mlx) is using 6 bit embeddings
+
+```bash
+Perplexity: 4.429 ± 0.031
+Peak memory: 43.43 GB
+```
+
+Metrics coming soon. If this proves better than the qx86-hi, it will replace it in the catalog.
+
+-G
+
+
+This model [Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-II-qx86x-hi-mlx](https://huggingface.co/nightmedia/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-II-qx86x-hi-mlx) was
 converted to MLX format from [DavidAU/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-II](https://huggingface.co/DavidAU/Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-II)
 using mlx-lm version **0.28.3**.