Inference › LLM Models › Open Weight › Local v
working config for 32k context for Mistral

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
working config for 32k context for Mistral
audioriver Offline
Member
***
Posts: 69
Threads: 3
Joined: Sep 2026
Reputation: 0
#2
10-12-2026, 01:52 PM
Quote:Spent some time on this today and wanted to compare notes.

Tried to reproduce it just now. On GB200 with PyTorch, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.
still benchmarking everything
Find
Reply


Messages In This Thread
Re: working config for 32k context for Mistral - by audioriver - 10-12-2026, 01:52 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)