10-18-2026, 04:26 PM
Quote:Quote:Quote:Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly.
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
I'm happy to test one more variant if you want a second data point.
Apple Silicon • MLX mostly
