+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: Apple / MLX (https://www.datasculpting.ai/inference/forumdisplay.php?fid=33)
+--- Thread: Apple unified memory limits (/showthread.php?tid=1253)
Apple unified memory limits - plainember52 - 10-14-2026
Did a bit of testing and thought I'd post the result here.
I tried this with DeepSeek using MLX on A6000. The headline result was better than I expected, but router policy still ended up being the limiting factor.
Happy to post more details if anyone wants them.
Re: Apple unified memory limits - sanescope - 10-15-2026
Appreciate the detail. I ended up in about the same place using Ollama. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: Apple unified memory limits - circuitwire58 - 10-15-2026
I'd start with the simpler stack.
Re: Apple unified memory limits - dockridge - 10-15-2026
Appreciate the detail. I ended up in about the same place using MLX.
Re: Apple unified memory limits - cudacrate - 10-15-2026
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
Re: Apple unified memory limits - visionyard23 - 10-15-2026
Quote:Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure show
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. Once you know the plain path works, then add the faster path back in piece by piece.
Re: Apple unified memory limits - turboyard94 - 10-15-2026
following this because I'm in the same boat.