+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: Ollama / LM Studio / Desktop Runtimes (https://www.datasculpting.ai/inference/forumdisplay.php?fid=38)
+--- Thread: best local runtime for mixed models (/showthread.php?tid=1289)
Pages:
1
2
Re: best local runtime for mixed models - vectorhouse71 - 10-18-2026
Quote:[quote]My first guess would be this: If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. A
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at NVFP4. Not glamorous advice, but repeatable baselines save a lot of time.
Re: best local runtime for mixed models - latentscope35 - 10-19-2026
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at prefill/decode split. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: best local runtime for mixed models - modgarden - 10-19-2026
I'd start with the simpler stack.
Re: best local runtime for mixed models - dockridge - 10-19-2026
What worked for me was pretty simple. If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: best local runtime for mixed models - dockridge - 10-19-2026
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly.
Re: best local runtime for mixed models - orbitbench6 - 10-19-2026
What worked for me was pretty simple. If you're on PyTorch, 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.