Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
distill or just quantize for Mistral
#11
Tried to reproduce it just now. On A6000 with Ollama, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed. The logs were somehow calmer than I was.
Reply


Messages In This Thread
Re: distill or just quantize for Mistral - by amberpatch25 - 10-19-2026, 02:57 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)