+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Performance Tuning (https://www.datasculpting.ai/inference/forumdisplay.php?fid=42)
+--- Thread: disaggregated inference thoughts on M3 Max (/showthread.php?tid=11)
Pages:
1
2
Re: disaggregated inference thoughts on M3 Max - kernelmike - 08-30-2026
subscribed, curious where this lands.
Re: disaggregated inference thoughts on M3 Max - quantsupply - 08-30-2026
Interesting, I hadn't tried that. I don't think your conclusion is far off.
Re: disaggregated inference thoughts on M3 Max - macropilot - 09-02-2026
Can you fill in a bit more context? What model, what runtime, and roughly what context size?
Re: disaggregated inference thoughts on M3 Max - kernelmike - 09-02-2026
Maybe, but I had the opposite result. I've seen people blame consumer GPUs when the real issue was much more mundane. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Re: disaggregated inference thoughts on M3 Max - tensorfield88 - 09-02-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there.