+- 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
4090 vs 5090 for 70B quants with TensorRT-LLM - turbogrid11 - 10-17-2026
I'm trying to sanity-check my setup.
My current setup is llama.cpp with 4090, and I keep running into workstation thermals.
Not looking for the perfect answer, mostly what worked in real use.
Re: 4090 vs 5090 for 70B quants with TensorRT-LLM - vrambandit - 10-17-2026
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.
Re: 4090 vs 5090 for 70B quants with TensorRT-LLM - rocmriley - 10-18-2026
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed. At this point the real bottleneck is my patience.
Re: 4090 vs 5090 for 70B quants with TensorRT-LLM - cudapoint - 10-18-2026
Thanks, that helps. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: 4090 vs 5090 for 70B quants with TensorRT-LLM - vrambandit - 10-18-2026
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.
Re: 4090 vs 5090 for 70B quants with TensorRT-LLM - embersmith - 10-18-2026
Tried to reproduce it just now. On GB200 with LM Studio, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.
Re: 4090 vs 5090 for 70B quants with TensorRT-LLM - batchwire - 10-18-2026
Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.
Re: 4090 vs 5090 for 70B quants with TensorRT-LLM - routecrate - 10-18-2026
I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher.
Re: 4090 vs 5090 for 70B quants with TensorRT-LLM - llmtrack - 10-18-2026
Interesting, I hadn't tried that. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: 4090 vs 5090 for 70B quants with TensorRT-LLM - amberhall - 10-19-2026
That matches what I was seeing. The pattern around structured output has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.