Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
search and retrieval tuning tips for Mixtral
#10
Tried to reproduce it just now. On M3 Max with MLX, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.
Reply


Messages In This Thread
Re: search and retrieval tuning tips for Mixtral - by cacheworks - 09-02-2026, 01:59 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)