Update README.md

README.md

@@ -13,6 +13,14 @@ library_name: mlx
 
 # unsloth-GLM-4.5-Air-qx64-mlx
 
+This is an experimental quant formula still under evaluation:
+```bash
+head, v_proj for first 4 layers set to 8 bit
+v_proj for the lower layers set to 6 bit
+all others set to 4 bit, quanted with group size 32
+```
+
+
 This model [unsloth-GLM-4.5-Air-qx64-mlx](https://huggingface.co/unsloth-GLM-4.5-Air-qx64-mlx) was
 converted to MLX format from [unsloth/GLM-4.5-Air](https://huggingface.co/unsloth/GLM-4.5-Air)
 using mlx-lm version **0.26.4**.