Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
4090 vs 5090 for 70B quants with TensorRT-LLM
#2
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at embeddings. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
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 - 10-17-2026, 10:51 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)