+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: LLM Models (https://www.datasculpting.ai/inference/forumdisplay.php?fid=12)
+--- Forum: Proprietary / Frontier (https://www.datasculpting.ai/inference/forumdisplay.php?fid=48)
+--- Thread: best local open-weight model this week: what are you seeing? (/showthread.php?tid=1099)
Pages:
1
2
best local open-weight model this week: what are you seeing? - oxideworks59 - 10-12-2026
Posting this in case it saves someone else a little time.
If you were starting from scratch today for this use case, what would you choose first and what would you ignore?
I'm especially interested in mistakes worth avoiding.
Re: best local open-weight model this week: what are you seeing? - edgecoast - 10-13-2026
What worked for me was pretty simple. On 7900 XTX, 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: best local open-weight model this week: what are you seeing? - mangohouse - 10-14-2026
Appreciate the detail. That matches what I saw on 7900 XTX. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: best local open-weight model this week: what are you seeing? - bytestack - 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.
Re: best local open-weight model this week: what are you seeing? - fastscope - 10-15-2026
Quote: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.
same here on my side.
Re: best local open-weight model this week: what are you seeing? - orbitgarden - 10-15-2026
Appreciate the detail. I don't think your conclusion is far off.
Re: best local open-weight model this week: what are you seeing? - sysstation69 - 10-15-2026
What exact setup are you running? Is this local-only or are you routing anything externally?
I'm happy to test one more variant if you want a second data point.
Re: best local open-weight model this week: what are you seeing? - routecraft - 10-15-2026
Quote:What exact setup are you running? Is this local-only or are you routing anything externally?
Interesting, I hadn't tried that. I ended up in about the same place using llama.cpp. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: best local open-weight model this week: what are you seeing? - southpatch - 10-16-2026
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Re: best local open-weight model this week: what are you seeing? - bytesupply76 - 10-16-2026
Thanks, that helps. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.