+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Miscellaneous Discussion (https://www.datasculpting.ai/inference/forumdisplay.php?fid=24)
+--- Forum: News & Industry (https://www.datasculpting.ai/inference/forumdisplay.php?fid=26)
+--- Thread: driver/framework news roundup for Qwen (/showthread.php?tid=1332)
Pages:
1
2
driver/framework news roundup for Qwen - modbench - 10-17-2026
Did a bit of testing and thought I'd post the result here.
I tried this with Mixtral using Ollama on M3 Max. The headline result was better than I expected, but prefill/decode split still ended up being the limiting factor.
Happy to post more details if anyone wants them.
If I had to summarize the lesson so far, it would be that clean setup and observability beat clever guesses.
Re: driver/framework news roundup for Qwen - kernelmike - 10-18-2026
A couple things I'd check first. On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time. Turns out 'just one more test' was a lie.
Re: driver/framework news roundup for Qwen - audiopoint18 - 10-18-2026
subscribed, curious where this lands.
Re: driver/framework news roundup for Qwen - deepseeked - 10-18-2026
A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?
Re: driver/framework news roundup for Qwen - bytestack - 10-18-2026
I tested this tonight. My result was mixed: first run looked bad, second run looked normal.
Re: driver/framework news roundup for Qwen - phaseshed - 10-18-2026
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal.
Re: driver/framework news roundup for Qwen - phaseshed - 10-18-2026
same here on my side.
Re: driver/framework news roundup for Qwen - bytestack - 10-18-2026
that fixed it for me too.
Re: driver/framework news roundup for Qwen - deepseeked - 10-18-2026
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly.
Re: driver/framework news roundup for Qwen - phaseshed - 10-18-2026
A couple questions before I guess too hard. Is this local-only or are you routing anything externally?