+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Hardware (https://www.datasculpting.ai/inference/forumdisplay.php?fid=4)
+--- Forum: GPUs (https://www.datasculpting.ai/inference/forumdisplay.php?fid=28)
+--- Thread: 4090 vs 5090 for 70B quants with TensorRT-LLM (/showthread.php?tid=1393)
Pages:
1
2
Re: 4090 vs 5090 for 70B quants with TensorRT-LLM - torchshed - 10-19-2026
Need a little more detail here. What model, what runtime, and roughly what context size?
Re: 4090 vs 5090 for 70B quants with TensorRT-LLM - fusedhall56 - 10-19-2026
Appreciate the detail. The pattern around router policy has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: 4090 vs 5090 for 70B quants with TensorRT-LLM - batchwire - 10-19-2026
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly.