+- 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: anyone testing this? (/showthread.php?tid=1314)
Pages:
1
2
best local open-weight model this week: anyone testing this? - dockworks23 - 10-15-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Just sharing a setup that ended up working reasonably well: FLUX, TensorRT-LLM, mini PC, with a lot of attention on tail latency.
Maybe useful as a starting point for newer folks.
Re: best local open-weight model this week: anyone testing this? - orbitbench6 - 10-15-2026
What worked for me was pretty simple. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: best local open-weight model this week: anyone testing this? - papermixer4 - 10-15-2026
worth checking the driver first.
Re: best local open-weight model this week: anyone testing this? - vectorhouse71 - 10-15-2026
worth checking the driver first.
Re: best local open-weight model this week: anyone testing this? - southtinker - 10-16-2026
Can you fill in a bit more context? Are you testing this on B200 or something else?
Re: best local open-weight model this week: anyone testing this? - dockworks23 - 10-16-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at consumer GPUs. Not glamorous advice, but repeatable baselines save a lot of time.
Re: best local open-weight model this week: anyone testing this? - bytelab - 10-16-2026
Quote:What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at consumer GPUs. Not gl
I'd start with the simpler stack.
Re: best local open-weight model this week: anyone testing this? - kernelghost - 10-16-2026
Quote:[quote]What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at consumer GPUs.
I hit almost the same issue last night.
Re: best local open-weight model this week: anyone testing this? - vectorpoint - 10-17-2026
What worked for me was pretty simple. On M3 Max, 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: anyone testing this? - fusedhall56 - 10-18-2026
Good point. That matches what I saw on dual 3090. The biggest change for me was simplifying the stack instead of adding one more optimization layer.