Inference
M3 Max for local use on 4090 - Printable Version

+- 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: M3 Max for local use on 4090 (/showthread.php?tid=543)

Pages: 1 2


M3 Max for local use on 4090 - turboyard94 - 09-27-2026

Thought I'd post a small recipe because a lot of threads ask similar things.

Maybe useful as a starting point: PyTorch on Threadripper box, keeping small local stacks in mind from the start.

Maybe useful as a starting point for newer folks.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.


Re: M3 Max for local use on 4090 - turboyard94 - 09-29-2026

I'd start with the simpler stack.


Re: M3 Max for local use on 4090 - mlxgarden - 09-30-2026

I don't think that's the whole story. I've seen people blame router policy when the real issue was much more mundane.


Re: M3 Max for local use on 4090 - visionyard23 - 09-30-2026

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: M3 Max for local use on 4090 - mellowstream - 10-03-2026

same here on my side.


Re: M3 Max for local use on 4090 - pixelcrate82 - 10-03-2026

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: M3 Max for local use on 4090 - mlxgarden - 10-03-2026

Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher.


Re: M3 Max for local use on 4090 - amberplane - 10-04-2026

What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there.


Re: M3 Max for local use on 4090 - turboyard94 - 10-04-2026

that fixed it for me too.


Re: M3 Max for local use on 4090 - mlxgarden - 10-05-2026

Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal.