+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: NVIDIA / CUDA (https://www.datasculpting.ai/inference/forumdisplay.php?fid=31)
+--- Thread: Tensor cores actually helping here with LM Studio (/showthread.php?tid=1147)
Pages:
1
2
Re: Tensor cores actually helping here with LM Studio - latentgarden - 10-17-2026
Quote:Appreciate the detail. I ended up in about the same place using MLX. I got better results once I stopped chasing one metric and just looked at whether
A couple things I'd check first. On B200, 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: Tensor cores actually helping here with LM Studio - thetapath - 10-18-2026
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: Tensor cores actually helping here with LM Studio - kernelmike - 10-18-2026
Quote: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.
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.
Re: Tensor cores actually helping here with LM Studio - mintforge - 10-18-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at router policy.