Update README.md

README.md

@@ -18,9 +18,17 @@ pipeline_tag: text-generation
 
 # INTELLECT-3-qx53g-mlx
 
-🏡 Insight: LIMI vs INTELLECT vs GLM-4.5-Air-Derestricted-qx53g
+Derestricted is quanted exactly the same and is a direct compare point.
+
+I picked a higher performing quant of LIMI in qx54g-hi for comparison.
+
+I am still waiting for the test results from qx53gx, it might be better, but this is the smallest you will get the model to work on a 64GB Mac while still being sort of good at things.
+
+These are the major differences:
+
+🏡 LIMI vs INTELLECT vs GLM-4.5-Air-Derestricted-qx53g
 ```data
-Feature		INTELLECT-3			LIMI Air-hi			Derestricted
+Feature		INTELLECT-3			LIMI Air-qx54g-hi	Derestricted
 BoolQ		✅✅ 0.820			0.378				0.431
 PIQA		✅ 0.772			✅ 776				0.769
 ARC			✅ 0.492 ARC_Easy	More balanced		Lowest
@@ -34,6 +42,7 @@ INTELLECT prioritizes logical depth and meta-cognition → ideal for reflective
 LIMI prioritizes grounded common-sense modeling → better suited for QA bots, summarization engines.
 
 -G
+
 This model [INTELLECT-3-qx53g-mlx](https://huggingface.co/nightmedia/INTELLECT-3-qx53g-mlx) was
 converted to MLX format from [PrimeIntellect/INTELLECT-3](https://huggingface.co/PrimeIntellect/INTELLECT-3)
 using mlx-lm version **0.28.4**.