+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: LLM Models (https://www.datasculpting.ai/inference/forumdisplay.php?fid=12)
+--- Forum: Open Weight (https://www.datasculpting.ai/inference/forumdisplay.php?fid=49)
+---- Forum: Local (https://www.datasculpting.ai/inference/forumdisplay.php?fid=51)
+---- Thread: working config for 32k context for FLUX (/showthread.php?tid=1294)
Pages:
1
2
Re: working config for 32k context for FLUX - deltagrid - 10-18-2026
Interesting, I hadn't tried that. I ended up in about the same place using TensorRT-LLM. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: working config for 32k context for FLUX - rocmcrate26 - 10-18-2026
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.
Re: working config for 32k context for FLUX - vectorport - 10-18-2026
I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Worth testing the simpler explanation before adopting the more interesting one.
Re: working config for 32k context for FLUX - vramstream - 10-18-2026
following this because I'm in the same boat.