Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
multimodal local stack that feels real for Qwen
#7
I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
Reply


Messages In This Thread
Re: multimodal local stack that feels real for Qwen - by cobalttinker - 10-03-2026, 12:17 AM

Forum Jump:


Users browsing this thread: 2 Guest(s)