Inference
quality tests for local assistants: anyone testing this? - Printable Version

+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Evaluation & Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=16)
+--- Forum: Evals (https://www.datasculpting.ai/inference/forumdisplay.php?fid=66)
+--- Thread: quality tests for local assistants: anyone testing this? (/showthread.php?tid=736)



quality tests for local assistants: anyone testing this? - audionode8 - 10-04-2026

Spent some time on this today and wanted to compare notes.

I've gone back and forth between SGLang and PyTorch for FLUX. The interesting difference for me has been NVFP4.

Trying to avoid rebuilding the whole thing twice.


Re: quality tests for local assistants: anyone testing this? - cudacrate - 10-05-2026

Need a little more detail here. Are you testing this on Threadripper box or something else?