Update README.md

README.md

@@ -24,6 +24,15 @@ base_model: cerebras/GLM-4.5-Air-REAP-82B-A12B
 
 # GLM-4.5-Air-REAP-82B-A12B-qx64g-hi-mlx
 
+```bash
+Model     Perplexity
+qx64g-hi  7.025 ± 0.063
+qx86g-hi  7.031 ± 0.064
+```
+
+This is a custom Deckard(qx) formula that enhances Air-specific layers
+
+
 This model [GLM-4.5-Air-REAP-82B-A12B-qx64g-hi-mlx](https://huggingface.co/GLM-4.5-Air-REAP-82B-A12B-qx64g-hi-mlx) was
 converted to MLX format from [cerebras/GLM-4.5-Air-REAP-82B-A12B](https://huggingface.co/cerebras/GLM-4.5-Air-REAP-82B-A12B)
 using mlx-lm version **0.28.3**.