+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: Other Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=39)
+--- Thread: NVFP4 / INT4 tradeoffs (/showthread.php?tid=1227)
Pages:
1
2
Re: NVFP4 / INT4 tradeoffs - sparrowcraft - 10-18-2026
Interesting, I hadn't tried that. The pattern around quant drift has been pretty similar for me.
Re: NVFP4 / INT4 tradeoffs - kernelmike - 10-18-2026
worth checking the driver first.
Re: NVFP4 / INT4 tradeoffs - sparrowhall - 10-19-2026
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly.
Re: NVFP4 / INT4 tradeoffs - quantyard - 10-19-2026
I'd approach it in a boring order. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.