+- 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: 8B vs 14B sweet spot (/showthread.php?tid=642)
Pages:
1
2
Re: 8B vs 14B sweet spot - kernelgrid - 10-06-2026
A couple things I'd check first. On 4090, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: 8B vs 14B sweet spot - orbitbench6 - 10-06-2026
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.
Re: 8B vs 14B sweet spot - vrambandit - 10-06-2026
Appreciate the detail. That matches what I saw on A6000. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: 8B vs 14B sweet spot - deepseeked - 10-06-2026
My first guess would be this: If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: 8B vs 14B sweet spot - macrotinker - 10-08-2026
same here on my side.
I'm happy to test one more variant if you want a second data point.