Update README.md

README.md

@@ -158,9 +158,9 @@ k_ffn = max(1, int(round(base_top_k * (0.5 + budget_ratio / 2.0))))
 
 | Budget Ratio | Active Attn Experts | Active FFN Experts | Relative Speed | Quality Retention | Recommended Use Case |
 |--------------|---------------------|--------------------|--------------:|------------------:|----------------------|
-| 1.0 (Full) | 6/6 (100%) | 2/4 (50%) | 1.0× | 100% | Maximum quality, complex reasoning |
-| 0.9 | 5-6/6 (83-100%) | 2/4 (50%) | ~1.1× | 95-98% | High-quality production |
-| 0.75 | 4-5/6 (67-83%) | 1-2/4 (25-50%) | ~1.4× | 90-95% | Balanced performance |
+| 1.0 (Full) | 6/6 (100%) | 1/4 (25%) | 1.0× | 100% | Maximum quality, complex reasoning |
+| 0.9 | 5-6/6 (83-100%) | 1/4 (25%) | ~1.1× | 95-98% | High-quality production |
+| 0.75 | 4-5/6 (67-83%) | 1/4 (25%) | ~1.4× | 90-95% | Balanced performance |
 | 0.6 | 4/6 (67%) | 1/4 (25%) | ~1.7× | 85-90% | Efficient inference |
 | 0.5 | 3/6 (50%) | 1/4 (25%) | ~2.0× | 80-85% | Fast generation, good quality |
 | 0.35 | 2-3/6 (33-50%) | 1/4 (25%) | ~2.3× | 70-80% | Speed-optimized |