+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Harnesses, Agents & Orchestration (https://www.datasculpting.ai/inference/forumdisplay.php?fid=11)
+--- Forum: Agents (https://www.datasculpting.ai/inference/forumdisplay.php?fid=44)
+--- Thread: distill or just quantize for Mistral (/showthread.php?tid=1144)
Pages:
1
2
distill or just quantize for Mistral - thetaplane - 10-13-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of LM Studio and M3 Max felt surprisingly usable once I tuned around small local stacks.
If someone wants the exact settings I can clean them up and post them.
Re: distill or just quantize for Mistral - northquill - 10-15-2026
What worked for me was pretty simple. On A6000, 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.
Re: distill or just quantize for Mistral - thetagrid15 - 10-15-2026
Thanks, that helps. That matches what I saw on mini PC. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: distill or just quantize for Mistral - vramridge - 10-17-2026
Tried to reproduce it just now. On dual 3090 with SGLang, I saw basically the same behavior.
Re: distill or just quantize for Mistral - torchtrack24 - 10-18-2026
same here on my side.
Re: distill or just quantize for Mistral - mangofield33 - 10-18-2026
That matches what I was seeing. The pattern around HBM constraints 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.
If you post your exact settings, people here can probably narrow it down pretty fast. I keep promising myself this is the last rebuild.
Re: distill or just quantize for Mistral - quietstack - 10-18-2026
Quote: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 o
Interesting, I hadn't tried that. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: distill or just quantize for Mistral - quietstack - 10-18-2026
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.
Re: distill or just quantize for Mistral - thetagrid15 - 10-18-2026
Appreciate the detail. The pattern around workstation thermals 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.
Re: distill or just quantize for Mistral - amberpatch25 - 10-19-2026
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.