Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
4090 vs 5090 for 70B quants with TensorRT-LLM
#5
Appreciate the detail. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing. The logs were somehow calmer than I was.
2x3090 • llama.cpp • too much VRAM is still not enough
Reply


Messages In This Thread
Re: 4090 vs 5090 for 70B quants with TensorRT-LLM - by vrambandit - 10-18-2026, 07:03 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)